Datasets:

ftopal

/

huggingface-models-embeddings

like 0

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # llama_2_13boasst_top1_2023_08_25_downproj_redonplat_r8_lr0.0001_g16 This model is a fine-tuned version of [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.0293 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: reduce_lr_on_plateau - lr_scheduler_warmup_steps: 0.05 - num_epochs: 1 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 1.2647 | 0.01 | 8 | 1.2528 | | 1.1928 | 0.02 | 16 | 1.1190 | | 1.1255 | 0.03 | 24 | 1.0739 | | 1.0741 | 0.04 | 32 | 1.0631 | | 1.0083 | 0.05 | 40 | 1.0568 | | 0.9729 | 0.06 | 48 | 1.0537 | | 1.0449 | 0.07 | 56 | 1.0503 | | 1.0403 | 0.08 | 64 | 1.0488 | | 1.0162 | 0.09 | 72 | 1.0469 | | 1.0393 | 0.1 | 80 | 1.0451 | | 0.9311 | 0.11 | 88 | 1.0441 | | 1.0532 | 0.12 | 96 | 1.0434 | | 1.0381 | 0.13 | 104 | 1.0427 | | 1.0845 | 0.14 | 112 | 1.0422 | | 1.0219 | 0.15 | 120 | 1.0410 | | 1.0452 | 0.16 | 128 | 1.0411 | | 1.0279 | 0.17 | 136 | 1.0405 | | 1.0164 | 0.19 | 144 | 1.0398 | | 0.9963 | 0.2 | 152 | 1.0397 | | 1.0477 | 0.21 | 160 | 1.0393 | | 1.0487 | 0.22 | 168 | 1.0382 | | 1.0536 | 0.23 | 176 | 1.0390 | | 1.0706 | 0.24 | 184 | 1.0392 | | 1.0821 | 0.25 | 192 | 1.0380 | | 1.0461 | 0.26 | 200 | 1.0378 | | 1.038 | 0.27 | 208 | 1.0373 | | 1.1003 | 0.28 | 216 | 1.0366 | | 1.0809 | 0.29 | 224 | 1.0371 | | 0.9842 | 0.3 | 232 | 1.0363 | | 1.0627 | 0.31 | 240 | 1.0354 | | 1.0546 | 0.32 | 248 | 1.0360 | | 1.0001 | 0.33 | 256 | 1.0357 | | 1.0134 | 0.34 | 264 | 1.0354 | | 1.0329 | 0.35 | 272 | 1.0358 | | 0.991 | 0.36 | 280 | 1.0360 | | 1.06 | 0.37 | 288 | 1.0357 | | 1.0374 | 0.38 | 296 | 1.0345 | | 1.0515 | 0.39 | 304 | 1.0343 | | 1.0658 | 0.4 | 312 | 1.0331 | | 1.0318 | 0.41 | 320 | 1.0331 | | 1.0068 | 0.42 | 328 | 1.0326 | | 0.9647 | 0.43 | 336 | 1.0334 | | 1.091 | 0.44 | 344 | 1.0338 | | 1.0422 | 0.45 | 352 | 1.0338 | | 1.0278 | 0.46 | 360 | 1.0335 | | 0.9569 | 0.47 | 368 | 1.0327 | | 1.0625 | 0.48 | 376 | 1.0331 | | 1.0068 | 0.49 | 384 | 1.0329 | | 0.9915 | 0.5 | 392 | 1.0324 | | 0.9923 | 0.51 | 400 | 1.0319 | | 1.0235 | 0.52 | 408 | 1.0323 | | 0.997 | 0.53 | 416 | 1.0322 | | 0.9955 | 0.55 | 424 | 1.0318 | | 1.0018 | 0.56 | 432 | 1.0316 | | 1.0133 | 0.57 | 440 | 1.0314 | | 1.0803 | 0.58 | 448 | 1.0315 | | 1.0108 | 0.59 | 456 | 1.0316 | | 1.0568 | 0.6 | 464 | 1.0311 | | 1.0083 | 0.61 | 472 | 1.0308 | | 1.0327 | 0.62 | 480 | 1.0313 | | 1.0731 | 0.63 | 488 | 1.0319 | | 0.9597 | 0.64 | 496 | 1.0322 | | 0.9742 | 0.65 | 504 | 1.0318 | | 1.0438 | 0.66 | 512 | 1.0327 | | 1.0511 | 0.67 | 520 | 1.0314 | | 1.0016 | 0.68 | 528 | 1.0316 | | 1.0382 | 0.69 | 536 | 1.0315 | | 1.0163 | 0.7 | 544 | 1.0314 | | 0.9667 | 0.71 | 552 | 1.0316 | | 0.9737 | 0.72 | 560 | 1.0310 | | 1.0067 | 0.73 | 568 | 1.0307 | | 1.0265 | 0.74 | 576 | 1.0304 | | 1.0096 | 0.75 | 584 | 1.0302 | | 0.9909 | 0.76 | 592 | 1.0301 | | 1.0551 | 0.77 | 600 | 1.0301 | | 1.0216 | 0.78 | 608 | 1.0300 | | 1.0245 | 0.79 | 616 | 1.0300 | | 1.0401 | 0.8 | 624 | 1.0301 | | 1.0262 | 0.81 | 632 | 1.0300 | | 0.969 | 0.82 | 640 | 1.0299 | | 0.9532 | 0.83 | 648 | 1.0299 | | 0.9809 | 0.84 | 656 | 1.0298 | | 1.0412 | 0.85 | 664 | 1.0299 | | 0.985 | 0.86 | 672 | 1.0297 | | 1.0318 | 0.87 | 680 | 1.0297 | | 1.0678 | 0.88 | 688 | 1.0296 | | 1.0092 | 0.89 | 696 | 1.0297 | | 1.0461 | 0.9 | 704 | 1.0298 | | 1.0206 | 0.92 | 712 | 1.0298 | | 1.0196 | 0.93 | 720 | 1.0297 | | 1.0591 | 0.94 | 728 | 1.0298 | | 0.9941 | 0.95 | 736 | 1.0295 | | 0.9883 | 0.96 | 744 | 1.0295 | | 1.0659 | 0.97 | 752 | 1.0295 | | 1.0179 | 0.98 | 760 | 1.0294 | | 1.0019 | 0.99 | 768 | 1.0293 | | 0.9779 | 1.0 | 776 | 1.0293 | ### Framework versions - Transformers 4.35.0.dev0 - Pytorch 2.1.0+cu121 - Datasets 2.5.2 - Tokenizers 0.14.0

{"tags": ["generated_from_trainer"], "base_model": "meta-llama/Llama-2-13b-hf", "model-index": [{"name": "llama_2_13boasst_top1_2023_08_25_downproj_redonplat_r8_lr0.0001_g16", "results": []}]}

imdatta0/llama_2_13boasst_top1_2023_08_25_downproj_redonplat_r8_lr0.0001_g16

2023-11-12T06:33:27+00:00

TAGS #generated_from_trainer #base_model-meta-llama/Llama-2-13b-hf #region-us

llama\_2\_13boasst\_top1\_2023\_08\_25\_downproj\_redonplat\_r8\_lr0.0001\_g16 ============================================================================== This model is a fine-tuned version of meta-llama/Llama-2-13b-hf on an unknown dataset. It achieves the following results on the evaluation set: * Loss: 1.0293 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0001 * train\_batch\_size: 1 * eval\_batch\_size: 1 * seed: 42 * gradient\_accumulation\_steps: 16 * total\_train\_batch\_size: 16 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: reduce\_lr\_on\_plateau * lr\_scheduler\_warmup\_steps: 0.05 * num\_epochs: 1 ### Training results ### Framework versions * Transformers 4.35.0.dev0 * Pytorch 2.1.0+cu121 * Datasets 2.5.2 * Tokenizers 0.14.0

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # AANN-Detector This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on a custom dataset that detects if a sentence contains the interesting "Indefinite Article + Adjective + Numeral + Noun" construction. For instance: *A beautiful five days* counts but "A five beautiful days" does not, since the numeral precedes the adjective. This idea was inspired by [Chris Potts' "obscure" classifier to detect the PiPP construction](https://huggingface.co/cgpotts/pipp-finder-bert-base-cased). ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Training results ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu121 - Datasets 2.2.1 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "bert-base-uncased", "pipeline_tag": "text-classification", "widget": [{"text": "The family met a lucky three students at the university of cambridge."}, {"text": "The family met three lucky students at the university of cambridge."}, {"text": "The family met three lucky a students at the university of cambridge."}, {"text": "This text does not contain any AANN constructions."}], "model-index": [{"name": "aann-detector", "results": []}]}

text-classification

kanishka/aann-detector

2023-11-12T06:36:52+00:00

TAGS #transformers #tensorboard #safetensors #bert #text-classification #generated_from_trainer #base_model-bert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us

# AANN-Detector This model is a fine-tuned version of bert-base-uncased on a custom dataset that detects if a sentence contains the interesting "Indefinite Article + Adjective + Numeral + Noun" construction. For instance: *A beautiful five days* counts but "A five beautiful days" does not, since the numeral precedes the adjective. This idea was inspired by Chris Potts' "obscure" classifier to detect the PiPP construction. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Training results ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu121 - Datasets 2.2.1 - Tokenizers 0.14.1

diffusers

# DreamBooth trained by AutoTrain Text encoder was not trained.

{"tags": ["text-to-image", "diffusers", "autotrain"], "base_model": "stabilityai/stable-diffusion-xl-base-1.0", "instance_prompt": "photo of sgk bottle", "inference": true}

text-to-image

MarioSAJavier/fanta-sdxl

2023-11-12T06:37:08+00:00

TAGS #diffusers #text-to-image #autotrain #base_model-stabilityai/stable-diffusion-xl-base-1.0 #has_space #region-us

# DreamBooth trained by AutoTrain Text encoder was not trained.

# **Q-Learning** Agent playing1 **FrozenLake-v1** This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** . ## Usage ```python model = load_from_hub(repo_id="lawyiu/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```

{"tags": ["FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "q-FrozenLake-v1-4x4-noSlippery", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "FrozenLake-v1-4x4-no_slippery", "type": "FrozenLake-v1-4x4-no_slippery"}, "metrics": [{"type": "mean_reward", "value": "1.00 +/- 0.00", "name": "mean_reward", "verified": false}]}]}]}

reinforcement-learning

lawyiu/q-FrozenLake-v1-4x4-noSlippery

2023-11-12T06:41:06+00:00

TAGS #FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us

# Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage

transformers

This is [NeverSleep/Nethena-20B](https://huggingface.co/NeverSleep/Nethena-20B) with [athirdpath/Nethena-20b-Glue-LORA](https://huggingface.co/athirdpath/Nethena-20b-Glue-LORA) applied. athirdpath/Nethena-20b-Glue-LORA is a 128 rank LORA for RP, trained on a private dataset. It is unalligned and NSFW-oriented. This is a test, exploring the effects of "gluing" the components of the 20b model together to reduce the iconic word replacement errors, increase lucidity, and improve recall.  The private ~500k token dataset used to train the LORA was Alpaca formatted and focused on 4 primary categories: - Medical texts (on psychology, reproductive organs, anatomy, and pregnancy). These are formatted so the model, in character as a doctor or therapist, answers a patient's question in short to medium form. - Excerpts from short stories and novellas (erotic and romantic) centered around both realistic and fantastic situations, covering several fetishes as well. These are sliced into ~2048 token chunks, and these long-form responses are all tied to the command “Enter narrator mode.” in the instructions. - A selection from PIPPA, using a wide keyword search for tokens associated with low quality human or AI data to remove those responses, then a positive search was done for words and phrases associated with a higher reading level. These are converted to Alpaca with “Enter RP mode.” in all the instruction fields. - ~18k tokens of GPT-4 generated data on role-playing from various characters’ perspectives, focusing on different situations and emotions. Includes many multi-turn conversations. So far it is passing subjective testing with flying colors, objective numbers coming soon. Trained with Alpaca-style prompts.

{"license": "cc-by-nc-4.0"}

text-generation

athirdpath/Nethena-20b-Glued

2023-11-12T06:43:09+00:00

TAGS #transformers #pytorch #llama #text-generation #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

This is NeverSleep/Nethena-20B with athirdpath/Nethena-20b-Glue-LORA applied. athirdpath/Nethena-20b-Glue-LORA is a 128 rank LORA for RP, trained on a private dataset. It is unalligned and NSFW-oriented. This is a test, exploring the effects of "gluing" the components of the 20b model together to reduce the iconic word replacement errors, increase lucidity, and improve recall. !image/png The private ~500k token dataset used to train the LORA was Alpaca formatted and focused on 4 primary categories: - Medical texts (on psychology, reproductive organs, anatomy, and pregnancy). These are formatted so the model, in character as a doctor or therapist, answers a patient's question in short to medium form. - Excerpts from short stories and novellas (erotic and romantic) centered around both realistic and fantastic situations, covering several fetishes as well. These are sliced into ~2048 token chunks, and these long-form responses are all tied to the command “Enter narrator mode.” in the instructions. - A selection from PIPPA, using a wide keyword search for tokens associated with low quality human or AI data to remove those responses, then a positive search was done for words and phrases associated with a higher reading level. These are converted to Alpaca with “Enter RP mode.” in all the instruction fields. - ~18k tokens of GPT-4 generated data on role-playing from various characters’ perspectives, focusing on different situations and emotions. Includes many multi-turn conversations. So far it is passing subjective testing with flying colors, objective numbers coming soon. Trained with Alpaca-style prompts.

peft

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.6.2.dev0

{"library_name": "peft", "base_model": "TinyPixel/Llama-2-7B-bf16-sharded"}

Hrithik2212/Dr.Llama2-7b-qlora-chat-experimental

2023-11-12T06:47:24+00:00

TAGS #peft #safetensors #arxiv-1910.09700 #base_model-TinyPixel/Llama-2-7B-bf16-sharded #region-us

# Model Card for Model ID ## Model Details ### Model Description - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact ## Training procedure The following 'bitsandbytes' quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.6.2.dev0

ml-agents

# **poca** Agent playing **SoccerTwos** This is a trained model of a **poca** agent playing **SoccerTwos** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: joshuaoreilly/poca-SoccerTwos 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀

{"library_name": "ml-agents", "tags": ["SoccerTwos", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SoccerTwos"]}

reinforcement-learning

joshuaoreilly/poca-SoccerTwos

2023-11-12T06:47:31+00:00

TAGS #ml-agents #tensorboard #onnx #SoccerTwos #deep-reinforcement-learning #reinforcement-learning #ML-Agents-SoccerTwos #region-us

# poca Agent playing SoccerTwos This is a trained model of a poca agent playing SoccerTwos using the Unity ML-Agents Library. ## Usage (with ML-Agents) The Documentation: URL We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your browser: URL - A *longer tutorial* to understand how works ML-Agents: URL ### Resume the training ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to URL 2. Step 1: Find your model_id: joshuaoreilly/poca-SoccerTwos 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play

transformers

Eileithyia-13B is an unaligned, roleplay oriented model created by merging [KoboldAI/LLaMA2-13B-TiefighterLR](https://huggingface.co/KoboldAI/LLaMA2-13B-TiefighterLR) with [a bespoke LORA](https://huggingface.co/athirdpath/Eileithyia-13B-LORA) trained directly on TiefighterLR. Eileithyia, as is the current trend, is named after a Greek goddess; in this case it is the goddess of childbirth and pregnancy.  The private ~400k token dataset used to train the LORA was Alpaca formatted and focused on 4 primary categories: - Medical texts (on pregnancy, reproductive organs, and impregnation). These are formatted so the model, in character as a doctor, answers a patient's question in short to medium form. - Excerpts from short stories and novellas (erotic, romantic, and platonic) centered around both realistic and fantastic pregnancy. These are sliced into ~2048 token chunks, and these long-form responses are all tied to the command “Enter narrator mode.” in the instructions. - A selection from [PIPPA](https://huggingface.co/datasets/PygmalionAI/PIPPA), using a wide keyword search for related terms then human curated (...the things I’ve seen…). These are converted to Alpaca with “Enter RP mode.” in all the instruction fields. - ~42k tokens of GPT-4 generated data on pregnancy from various characters’ perspectives, focusing on different responses and stages. Also includes a synopsis for each week in various styles. - ~18k tokens of GPT-4 generated data on non-maternal role-playing from various characters’ perspectives, focusing on different situations and emotions. Includes many multi-turn conversations. Testing is still in progress.

{"tags": ["not-for-all-audiences"]}

text-generation

athirdpath/Eileithyia-13B

2023-11-12T06:52:12+00:00

TAGS #transformers #pytorch #llama #text-generation #not-for-all-audiences #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

Eileithyia-13B is an unaligned, roleplay oriented model created by merging KoboldAI/LLaMA2-13B-TiefighterLR with a bespoke LORA trained directly on TiefighterLR. Eileithyia, as is the current trend, is named after a Greek goddess; in this case it is the goddess of childbirth and pregnancy. !image/png The private ~400k token dataset used to train the LORA was Alpaca formatted and focused on 4 primary categories: - Medical texts (on pregnancy, reproductive organs, and impregnation). These are formatted so the model, in character as a doctor, answers a patient's question in short to medium form. - Excerpts from short stories and novellas (erotic, romantic, and platonic) centered around both realistic and fantastic pregnancy. These are sliced into ~2048 token chunks, and these long-form responses are all tied to the command “Enter narrator mode.” in the instructions. - A selection from PIPPA, using a wide keyword search for related terms then human curated (...the things I’ve seen…). These are converted to Alpaca with “Enter RP mode.” in all the instruction fields. - ~42k tokens of GPT-4 generated data on pregnancy from various characters’ perspectives, focusing on different responses and stages. Also includes a synopsis for each week in various styles. - ~18k tokens of GPT-4 generated data on non-maternal role-playing from various characters’ perspectives, focusing on different situations and emotions. Includes many multi-turn conversations. Testing is still in progress.

# **Q-Learning** Agent playing1 **Taxi-v3** This is a trained model of a **Q-Learning** agent playing **Taxi-v3** . ## Usage ```python model = load_from_hub(repo_id="lawyiu/Q-learning-taxi-v3", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```

{"tags": ["Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "Q-learning-taxi-v3", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "Taxi-v3", "type": "Taxi-v3"}, "metrics": [{"type": "mean_reward", "value": "7.56 +/- 2.71", "name": "mean_reward", "verified": false}]}]}]}

reinforcement-learning

lawyiu/Q-learning-taxi-v3

2023-11-12T06:55:01+00:00

TAGS #Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us

# Q-Learning Agent playing1 Taxi-v3 This is a trained model of a Q-Learning agent playing Taxi-v3 . ## Usage

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{}

text2text-generation

shashwat1225/0.8-threshold-finetuned-m2m

2023-11-12T06:56:52+00:00

TAGS #transformers #safetensors #m2m_100 #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us

# Model Card for Model ID This modelcard aims to be a base template for new models. It has been generated using this raw template. ## Model Details ### Model Description - Developed by: - Funded by [optional]: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact

# Juggernaut XL Version 6 + RunDiffusion Original model: https://civitai.com/models/133005/juggernaut-xl Fused with the [lcm-lora-sdxl](https://huggingface.co/latent-consistency/lcm-lora-sdxl) so it can be used as a pure LCM model. | | | | | |--|--|--|--| |||||

{"license": "openrail++", "tags": ["text-to-image", "stable-diffusion", "distilled-model"], "inference": false}

text-to-image

OzzyGT/lcm-juggernaut-xl

2023-11-12T07:07:00+00:00

TAGS #text-to-image #stable-diffusion #distilled-model #license-openrail++ #region-us

Juggernaut XL Version 6 + RunDiffusion ====================================== Original model: URL Fused with the lcm-lora-sdxl so it can be used as a pure LCM model.

peft

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: QuantizationMethod.BITS_AND_BYTES - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.7.0.dev0

{"library_name": "peft", "base_model": "meta-llama/Llama-2-7b-hf"}

SebasMena111/llama2-spanish-128

2023-11-12T07:13:06+00:00

TAGS #peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Llama-2-7b-hf #region-us

# Model Card for Model ID ## Model Details ### Model Description - Developed by: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact ## Training procedure The following 'bitsandbytes' quantization config was used during training: - quant_method: QuantizationMethod.BITS_AND_BYTES - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.7.0.dev0

transformers

# training This model is a fine-tuned version of [huggingface/CodeBERTa-small-v1](https://huggingface.co/huggingface/CodeBERTa-small-v1) on an [my a dataset curated from The Technical Debt Dataset](https://huggingface.co/datasets/davidgaofc/techdebt). # dataset citation Valentina Lenarduzzi, Nyyti Saarimäki, Davide Taibi. The Technical Debt Dataset. Proceedings for the 15th Conference on Predictive Models and Data Analytics in Software Engineering. Brazil. 2019. ## Model description Classifies cleaned diffs of code. * 1: exhibits possible technical debt * 0: is probably clean ## Intended uses & limitations Limited by many things probably, use with caution. Improvements in progress. ## Training and evaluation data ~95% accurate on the test split of dataset above ~.94 F1 score on test split of dataset above. ## Training procedure One epoch of training done on the dataset above. ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 30 - eval_batch_size: 30 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1

{"tags": ["generated_from_trainer"], "base_model": "huggingface/CodeBERTa-small-v1", "model-index": [{"name": "training", "results": []}]}

text-classification

davidgaofc/TechDebtClassifier

2023-11-12T07:13:35+00:00

TAGS #transformers #tensorboard #safetensors #roberta #text-classification #generated_from_trainer #base_model-huggingface/CodeBERTa-small-v1 #autotrain_compatible #endpoints_compatible #has_space #region-us

# training This model is a fine-tuned version of huggingface/CodeBERTa-small-v1 on an my a dataset curated from The Technical Debt Dataset. # dataset citation Valentina Lenarduzzi, Nyyti Saarimäki, Davide Taibi. The Technical Debt Dataset. Proceedings for the 15th Conference on Predictive Models and Data Analytics in Software Engineering. Brazil. 2019. ## Model description Classifies cleaned diffs of code. * 1: exhibits possible technical debt * 0: is probably clean ## Intended uses & limitations Limited by many things probably, use with caution. Improvements in progress. ## Training and evaluation data ~95% accurate on the test split of dataset above ~.94 F1 score on test split of dataset above. ## Training procedure One epoch of training done on the dataset above. ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 30 - eval_batch_size: 30 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1

diffusers

### Emojis_SD21_2000 Dreambooth model trained by YB23code with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb) Sample pictures of this concept:

{"license": "creativeml-openrail-m", "tags": ["text-to-image", "stable-diffusion"]}

text-to-image

YB23code/emojis-sd21-2000

2023-11-12T07:22:03+00:00

TAGS #diffusers #text-to-image #stable-diffusion #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us

### Emojis_SD21_2000 Dreambooth model trained by YB23code with TheLastBen's fast-DreamBooth notebook Test the concept via A1111 Colab fast-Colab-A1111 Sample pictures of this concept:

diffusers

# LoRA DreamBooth - katie312/dreambooth_fundus_model These are LoRA adaption weights for /home/katie/stable-diffusion-2-1. The weights were trained on a photo of non-diabetic retinopathy fundus using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following.     LoRA for the text encoder was enabled: False.

{"license": "creativeml-openrail-m", "tags": ["stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "diffusers", "lora"], "base_model": "/home/katie/stable-diffusion-2-1", "instance_prompt": "a photo of non-diabetic retinopathy fundus", "inference": true}

text-to-image

katie312/dreambooth_fundus_model

2023-11-12T07:28:28+00:00

TAGS #diffusers #stable-diffusion #stable-diffusion-diffusers #text-to-image #lora #license-creativeml-openrail-m #region-us

# LoRA DreamBooth - katie312/dreambooth_fundus_model These are LoRA adaption weights for /home/katie/stable-diffusion-2-1. The weights were trained on a photo of non-diabetic retinopathy fundus using DreamBooth. You can find some example images in the following. !img_0 !img_1 !img_2 !img_3 LoRA for the text encoder was enabled: False.

transformers

Made by finetuning [t5-small](https://huggingface.co/t5-small).

{}

text2text-generation

aboli-marathe/t5small_best

2023-11-12T07:28:37+00:00

TAGS #transformers #safetensors #t5 #text2text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

Made by finetuning t5-small.

stable-baselines3

# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4** This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga lawyiu -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga lawyiu -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga lawyiu ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 200000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 200000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```

{"library_name": "stable-baselines3", "tags": ["SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "DQN", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "SpaceInvadersNoFrameskip-v4", "type": "SpaceInvadersNoFrameskip-v4"}, "metrics": [{"type": "mean_reward", "value": "257.00 +/- 38.81", "name": "mean_reward", "verified": false}]}]}]}

reinforcement-learning

lawyiu/SpaceInvaders-v4-DQN

2023-11-12T07:38:15+00:00

TAGS #stable-baselines3 #SpaceInvadersNoFrameskip-v4 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us

# DQN Agent playing SpaceInvadersNoFrameskip-v4 This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4 using the stable-baselines3 library and the RL Zoo. The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: URL SB3: URL SB3 Contrib: URL Install the RL Zoo (with SB3 and SB3-Contrib): If you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do: ## Training (with the RL Zoo) ## Hyperparameters # Environment Arguments

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # llama2_finetuned_chatbot This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10 ### Training results ### Framework versions - Transformers 4.30.2 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.13.3

{"tags": ["generated_from_trainer"], "model-index": [{"name": "llama2_finetuned_chatbot", "results": []}]}

roshnidevadiga/llama2_finetuned_chatbot

2023-11-12T07:38:47+00:00

TAGS #tensorboard #generated_from_trainer #region-us

# llama2_finetuned_chatbot This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10 ### Training results ### Framework versions - Transformers 4.30.2 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.13.3

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-finetuned-squad This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset. It achieves the following results on the evaluation set: - Loss: 1.1624 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 1.2202 | 1.0 | 5533 | 1.1500 | | 0.951 | 2.0 | 11066 | 1.1284 | | 0.7434 | 3.0 | 16599 | 1.1624 | ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu118 - Datasets 2.15.0 - Tokenizers 0.15.0

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["squad"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "distilbert-base-uncased-finetuned-squad", "results": []}]}

question-answering

gaya/distilbert-base-uncased-finetuned-squad

2023-11-12T07:44:37+00:00

TAGS #transformers #tensorboard #safetensors #distilbert #question-answering #generated_from_trainer #dataset-squad #base_model-distilbert-base-uncased #license-apache-2.0 #endpoints_compatible #region-us

distilbert-base-uncased-finetuned-squad ======================================= This model is a fine-tuned version of distilbert-base-uncased on the squad dataset. It achieves the following results on the evaluation set: * Loss: 1.1624 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 2e-05 * train\_batch\_size: 16 * eval\_batch\_size: 16 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * num\_epochs: 3 ### Training results ### Framework versions * Transformers 4.35.2 * Pytorch 2.1.0+cu118 * Datasets 2.15.0 * Tokenizers 0.15.0

# Howdy These are a few test models I made using (and for use with) [DDSP-SVC](https://github.com/yxlllc/DDSP-SVC). I am not experienced with this software or technology, but hope to provide samples which facilitate adoption and interest in this project and associated technologies. All models are based on 44.1khz samples from a English speakers, though thanks to [DDSP](https://magenta.tensorflow.org/ddsp), they're generally fairly decent with use in a variety of other languages. Training is done following the suggestions and best practices according to the DDSP-SVC project, with initial learning rates ranging between 0.00010 and 0.00020. If using DDSP-SVC's **gui_diff.py**, keep in mind that pitch adjustment is probably required if your voice is deeper than the character. For any/all questions/comments/suggestions, please use the Community section here. ## Models - PrimReaper - (Stereo) Trained on YouTube content from popular YouTuber "The Prim Reaper" - Panam - (Mono) Trained on extracted audio content from the Cyberpunk 2077 character dialogue named "Panam" - V-F - (Mono) Trained on extracted dialogue audio from the Female "V" character in Cyberpunk 2077 - Nora - (Mono) Trained on Fallout 4 dialogue audio from the game character "Nora" ## Usage To use these, place the model file (model_XXXXXX.pt) and configuration file (config.yaml) in a directory. **It's rather important to mention that each model file should be in a distinct directory with its accompanying config.yaml or your results may be off/weird/broken.** ## Settings For realtime inference, my settings are generally as follows: **Normal Settings** - Speaker ID: Always "1" - Response Threshold: -45 (This is mic specific) - Pitch: 10 - 15 depending on model - Sampling rate: Always 44100 for my models - Mix Speaker: All models are single-speaker, so this is **not** checked **Performance Settings** - Segmentation Size: 0.45 - Cross fade duration: 0.07 - Historical blocks used: 8 - f0Extractor: rmvpe - Phase vocoder: Depending on the model I enable it if model output feels robotic/stuttery, and disable if it sounds "buttery" **Diffusion Settings** - K-steps: 200 - Speedup: 10 - Diffusion method: ddim or pndm, depending on model - Encode silence: Depends on the model, but usually "on" for the best quality

{"language": ["en"], "license": "creativeml-openrail-m", "tags": ["voice-to-voice", "ddsp-svc"], "pipeline_tag": "audio-to-audio"}

audio-to-audio

danieloneill/ddsp-svc-samplemodels-en

2023-11-12T07:46:27+00:00

TAGS #voice-to-voice #ddsp-svc #audio-to-audio #en #license-creativeml-openrail-m #region-us

# Howdy These are a few test models I made using (and for use with) DDSP-SVC. I am not experienced with this software or technology, but hope to provide samples which facilitate adoption and interest in this project and associated technologies. All models are based on 44.1khz samples from a English speakers, though thanks to DDSP, they're generally fairly decent with use in a variety of other languages. Training is done following the suggestions and best practices according to the DDSP-SVC project, with initial learning rates ranging between 0.00010 and 0.00020. If using DDSP-SVC's gui_diff.py, keep in mind that pitch adjustment is probably required if your voice is deeper than the character. For any/all questions/comments/suggestions, please use the Community section here. ## Models - PrimReaper - (Stereo) Trained on YouTube content from popular YouTuber "The Prim Reaper" - Panam - (Mono) Trained on extracted audio content from the Cyberpunk 2077 character dialogue named "Panam" - V-F - (Mono) Trained on extracted dialogue audio from the Female "V" character in Cyberpunk 2077 - Nora - (Mono) Trained on Fallout 4 dialogue audio from the game character "Nora" ## Usage To use these, place the model file (model_XXXXXX.pt) and configuration file (URL) in a directory. It's rather important to mention that each model file should be in a distinct directory with its accompanying URL or your results may be off/weird/broken. ## Settings For realtime inference, my settings are generally as follows: Normal Settings - Speaker ID: Always "1" - Response Threshold: -45 (This is mic specific) - Pitch: 10 - 15 depending on model - Sampling rate: Always 44100 for my models - Mix Speaker: All models are single-speaker, so this is not checked Performance Settings - Segmentation Size: 0.45 - Cross fade duration: 0.07 - Historical blocks used: 8 - f0Extractor: rmvpe - Phase vocoder: Depending on the model I enable it if model output feels robotic/stuttery, and disable if it sounds "buttery" Diffusion Settings - K-steps: 200 - Speedup: 10 - Diffusion method: ddim or pndm, depending on model - Encode silence: Depends on the model, but usually "on" for the best quality

transformers

Made by finetuning [t5-small](https://huggingface.co/t5-small).

{}

text2text-generation

aboli-marathe/t5small_31

2023-11-12T07:51:18+00:00

TAGS #transformers #safetensors #t5 #text2text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

Made by finetuning t5-small.

diffusers

### Emojis_SD14_2000 Dreambooth model trained by YB23code with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb) Sample pictures of this concept:

{"license": "creativeml-openrail-m", "tags": ["text-to-image", "stable-diffusion"]}

text-to-image

YB23code/emojis-sd14-2000

2023-11-12T07:53:01+00:00

TAGS #diffusers #safetensors #text-to-image #stable-diffusion #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us

### Emojis_SD14_2000 Dreambooth model trained by YB23code with TheLastBen's fast-DreamBooth notebook Test the concept via A1111 Colab fast-Colab-A1111 Sample pictures of this concept:

transformers

# The Skipped Beat: A Study of Sociopragmatic Understanding in LLMs for 64 Languages <p align="center"> <a href="https://chiyuzhang94.github.io/" target="_blank">Chiyu Zhang</a>, Khai Duy Doan, Qisheng Liao, <a href="https://mageed.arts.ubc.ca/" target="_blank">Muhammad Abdul-Mageed</a></p> <p align="center" float="left"> <p align="center" float="left"> The University of British Columbia, Mohamed bin Zayed University of Artificial Intelligence </p> <p align="center">Publish at Main Conference of EMNLP 2023</p> <p align="center"> <a href="https://arxiv.org/abs/2310.14557" target="_blank">Paper</a></p> []() []() ## Checkpoints of Models Pre-Trained with InfoDCL We further pretrained XLMR/RoBERTa with InfoDCL framework by ([Zhang et al. 2023](https://aclanthology.org/2023.findings-acl.152/)) Multilingual Model: * InfoDCL-XLMR trained with multilingual TweetEmoji-multi: https://huggingface.co/UBC-NLP/InfoDCL-Emoji-XLMR-Base English Models: * InfoDCL-RoBERTa trained with TweetEmoji-EN: https://huggingface.co/UBC-NLP/InfoDCL-emoji * InfoDCL-RoBERTa trained with TweetHashtag-EN: https://huggingface.co/UBC-NLP/InfoDCL-hashtag ## Citation Please cite us if you find our data or models useful. ```bibtex @inproceedings{zhang-etal-2023-skipped, title = "The Skipped Beat: A Study of Sociopragmatic Understanding in LLMs for 64 Languages", author = "Zhang, Chiyu and Khai Duy Doan and, Qisheng Liao and, Abdul-Mageed, Muhammad", booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP)", year = "2023", publisher = "Association for Computational Linguistics", } ```

{"language": ["en"], "license": "cc", "library_name": "transformers", "tags": ["social media", "contrastive learning"]}

feature-extraction

UBC-NLP/InfoDCL-Emoji-XLMR-Base

2023-11-12T07:59:36+00:00

TAGS #transformers #pytorch #xlm-roberta #feature-extraction #social media #contrastive learning #en #arxiv-2310.14557 #license-cc #endpoints_compatible #region-us

# The Skipped Beat: A Study of Sociopragmatic Understanding in LLMs for 64 Languages <p align="center"> <a href="URL target="_blank">Chiyu Zhang</a>, Khai Duy Doan, Qisheng Liao, <a href="URL target="_blank">Muhammad Abdul-Mageed</a></p> <p align="center" float="left"> <p align="center" float="left"> The University of British Columbia, Mohamed bin Zayed University of Artificial Intelligence </p> <p align="center">Publish at Main Conference of EMNLP 2023</p> <p align="center"> <a href="URL target="_blank">Paper</a></p> ![Code License]() ![Data License]() ## Checkpoints of Models Pre-Trained with InfoDCL We further pretrained XLMR/RoBERTa with InfoDCL framework by (Zhang et al. 2023) Multilingual Model: * InfoDCL-XLMR trained with multilingual TweetEmoji-multi: URL English Models: * InfoDCL-RoBERTa trained with TweetEmoji-EN: URL * InfoDCL-RoBERTa trained with TweetHashtag-EN: URL Please cite us if you find our data or models useful.

diffusers

# Nicky Ferrari <Gallery /> ## Model description Modelo de Nicky Ferrari ## Trigger words You should use `NickyFerrari` to trigger the image generation. You should use `MILF` to trigger the image generation. You should use `Nicky Ferrari` to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](/HankMoody1980/NickyFerrari/tree/main) them in the Files & versions tab.

{"license": "artistic-2.0", "tags": ["text-to-image", "stable-diffusion", "lora", "diffusers", "template:sd-lora"], "widget": [{"text": "La mejor calidad, 4k, 8k, Altas Resoluciones, Obra maestra:1.2, Ultra detallado, realista:1.37, (Cinematographer, cuerpo completo), (Hermosa cara detallada, hermosos ojos detallados, hermosos labios detallados), (Modelo Latina, Milf), (Glamuroso, seductor), (posando en un estudio con luz de estudio), (colores vibrantes, alto contraste), (Soft natural lighting), (Sensual, seductor), (Vestimenta provocativa), (Cabello largo y suelto), (Piel impecable), (photo studio shoot), (mirada caliente), (Postura sexual), (Maquillaje llamativo), (Joyas exquisitas), (Accesorios elegantes), (intense expression), (Belleza cautivadora), (Meticulous Attention to Detail), (Professional Photography), (Striking Composition), (encanto femenino), (Figura de reloj de arena), (Perfectly manicured nails), (Pose erotica), (ojos expresivos), (Curvas deseables), (Ambiente estudio neutro con fondo rosa), (Shadows Dramatic), (Sculpted features), (tez radiante), (Presencia inolvidable), (enigmatic aura), (Sonrisa deslumbrante), (Estilo sofisticado), (fondo neutral limpio), (Confianza sin remordimientos), (Encanto cautivador), (stunning images), (artistic rendition), (Foto de glamour), (attention-grabbing), (Impacto inolvidable), (Hypnotic magnetism), (Belleza poco convencional), (Elegancia atemporal), (Glamour inolvidable), (Vestuario stripper), (estiletto shoes:1), (Carisma irresistible), (Expresiones provocativas), (Sensual appeal), (Fascinating composition), (Retrato inolvidable), (poses sugestivas), (posando sexualmente), (pose erotica), (cuerpo completo:1).", "output": {"url": "images/273878f896fde368f3c6b910d354b2b4ee84a90e.png"}}, {"text": "La mejor calidad, 4k, 8k, Altas Resoluciones, Obra maestra:1.2, Ultra detallado, realista:1.37, (Cinematographer, cuerpo completo), (Hermosa cara detallada, hermosos ojos detallados, hermosos labios detallados), (Modelo Latina, Milf), (Glamuroso, seductor), (posando en un estudio con luz de estudio), (colores vibrantes, alto contraste), (Soft natural lighting), (Sensual, seductor), (Vestimenta provocativa), (Cabello largo y suelto), (Piel impecable), (photo studio shoot), (mirada caliente), (Postura sexual), (Maquillaje llamativo), (Joyas exquisitas), (Accesorios elegantes), (intense expression), (Belleza cautivadora), (Meticulous Attention to Detail), (Professional Photography), (Striking Composition), (encanto femenino), (Figura de reloj de arena), (Perfectly manicured nails), (Pose erotica), (ojos expresivos), (Curvas deseables), (Ambiente estudio neutro con fondo rosa), (Shadows Dramatic), (Sculpted features), (tez radiante), (Presencia inolvidable), (enigmatic aura), (Sonrisa deslumbrante), (Estilo sofisticado), (fondo neutral limpio), (Confianza sin remordimientos), (Encanto cautivador), (stunning images), (artistic rendition), (Foto de glamour), (attention-grabbing), (Impacto inolvidable), (Hypnotic magnetism), (Belleza poco convencional), (Elegancia atemporal), (Glamour inolvidable), (Vestuario stripper), (estiletto shoes:1), (Carisma irresistible), (Expresiones provocativas), (Sensual appeal), (Fascinating composition), (Retrato inolvidable), (poses sugestivas), (posando sexualmente), (pose erotica), (cuerpo completo:1).", "output": {"url": "images/761f63bfba158e68e792dda2b6b6bf36f662dd60.png"}}, {"text": "La mejor calidad, 4k, 8k, Altas Resoluciones, Obra maestra:1.2, Ultra detallado, realista:1.37, (Cinematographer, cuerpo completo), (Hermosa cara detallada, hermosos ojos detallados, hermosos labios detallados), (Modelo Latina, Milf), (Glamuroso, seductor), (posando en un estudio con luz de estudio), (colores vibrantes, alto contraste), (Soft natural lighting), (Sensual, seductor), (Vestimenta provocativa), (Cabello largo y suelto), (Piel impecable), (photo studio shoot), (mirada caliente), (Postura sexual), (Maquillaje llamativo), (Joyas exquisitas), (Accesorios elegantes), (intense expression), (Belleza cautivadora), (Meticulous Attention to Detail), (Professional Photography), (Striking Composition), (encanto femenino), (Figura de reloj de arena), (Perfectly manicured nails), (Pose erotica), (ojos expresivos), (Curvas deseables), (Ambiente estudio neutro con fondo rosa), (Shadows Dramatic), (Sculpted features), (tez radiante), (Presencia inolvidable), (enigmatic aura), (Sonrisa deslumbrante), (Estilo sofisticado), (fondo neutral limpio), (Confianza sin remordimientos), (Encanto cautivador), (stunning images), (artistic rendition), (Foto de glamour), (attention-grabbing), (Impacto inolvidable), (Hypnotic magnetism), (Belleza poco convencional), (Elegancia atemporal), (Glamour inolvidable), (Vestuario stripper), (estiletto shoes:1), (Carisma irresistible), (Expresiones provocativas), (Sensual appeal), (Fascinating composition), (Retrato inolvidable), (poses sugestivas), (posando sexualmente), (pose erotica), (cuerpo completo:1).", "output": {"url": "images/912afc9dc33fd140284c2a2fcfca581f426166ad.png"}}, {"text": "La mejor calidad, 4k, 8k, Altas Resoluciones, Obra maestra:1.2, Ultra detallado, realista:1.37, (Cinematographer, cuerpo completo), (Hermosa cara detallada, hermosos ojos detallados, hermosos labios detallados), (Modelo Latina, Milf), (Glamuroso, seductor), (posando en un estudio con luz de estudio), (colores vibrantes, alto contraste), (Soft natural lighting), (Sensual, seductor), (Vestimenta provocativa), (Cabello largo y suelto), (Piel impecable), (photo studio shoot), (mirada caliente), (Postura sexual), (Maquillaje llamativo), (Joyas exquisitas), (Accesorios elegantes), (intense expression), (Belleza cautivadora), (Meticulous Attention to Detail), (Professional Photography), (Striking Composition), (encanto femenino), (Figura de reloj de arena), (Perfectly manicured nails), (Pose erotica), (ojos expresivos), (Curvas deseables), (Ambiente estudio neutro con fondo rosa), (Shadows Dramatic), (Sculpted features), (tez radiante), (Presencia inolvidable), (enigmatic aura), (Sonrisa deslumbrante), (Estilo sofisticado), (fondo neutral limpio), (Confianza sin remordimientos), (Encanto cautivador), (stunning images), (artistic rendition), (Foto de glamour), (attention-grabbing), (Impacto inolvidable), (Hypnotic magnetism), (Belleza poco convencional), (Elegancia atemporal), (Glamour inolvidable), (Vestuario stripper), (estiletto shoes:1), (Carisma irresistible), (Expresiones provocativas), (Sensual appeal), (Fascinating composition), (Retrato inolvidable), (poses sugestivas), (posando sexualmente), (pose erotica), (cuerpo completo:1).", "output": {"url": "images/3866a5ac66f011dc4bff95e22bf459abfc9d5af2.png"}}, {"text": "La mejor calidad, 4k, 8k, Altas Resoluciones, Obra maestra:1.2, Ultra detallado, realista:1.37, (Cinematographer, cuerpo completo), (Hermosa cara detallada, hermosos ojos detallados, hermosos labios detallados), (Modelo Latina, Milf), (Glamuroso, seductor), (posando en un estudio con luz de estudio), (colores vibrantes, alto contraste), (Soft natural lighting), (Sensual, seductor), (Vestimenta provocativa), (Cabello largo y suelto), (Piel impecable), (photo studio shoot), (mirada caliente), (Postura sexual), (Maquillaje llamativo), (Joyas exquisitas), (Accesorios elegantes), (intense expression), (Belleza cautivadora), (Meticulous Attention to Detail), (Professional Photography), (Striking Composition), (encanto femenino), (Figura de reloj de arena), (Perfectly manicured nails), (Pose erotica), (ojos expresivos), (Curvas deseables), (Ambiente estudio neutro con fondo rosa), (Shadows Dramatic), (Sculpted features), (tez radiante), (Presencia inolvidable), (enigmatic aura), (Sonrisa deslumbrante), (Estilo sofisticado), (fondo neutral limpio), (Confianza sin remordimientos), (Encanto cautivador), (stunning images), (artistic rendition), (Foto de glamour), (attention-grabbing), (Impacto inolvidable), (Hypnotic magnetism), (Belleza poco convencional), (Elegancia atemporal), (Glamour inolvidable), (Vestuario stripper), (estiletto shoes:1), (Carisma irresistible), (Expresiones provocativas), (Sensual appeal), (Fascinating composition), (Retrato inolvidable), (poses sugestivas), (posando sexualmente), (pose erotica), (cuerpo completo:1).", "output": {"url": "images/9315d2c30696aa64d23875e1fd107d57907f06f0.png"}}, {"text": "La mejor calidad, 4k, 8k, Altas Resoluciones, Obra maestra:1.2, Ultra detallado, realista:1.37, (Cinematographer, cuerpo completo), (Hermosa cara detallada, hermosos ojos detallados, hermosos labios detallados), (Modelo Latina, Milf), (Glamuroso, seductor), (posando en un estudio con luz de estudio), (colores vibrantes, alto contraste), (Soft natural lighting), (Sensual, seductor), (Vestimenta provocativa), (Cabello largo y suelto), (Piel impecable), (photo studio shoot), (mirada caliente), (Postura sexual), (Maquillaje llamativo), (Joyas exquisitas), (Accesorios elegantes), (intense expression), (Belleza cautivadora), (Meticulous Attention to Detail), (Professional Photography), (Striking Composition), (encanto femenino), (Figura de reloj de arena), (Perfectly manicured nails), (Pose erotica), (ojos expresivos), (Curvas deseables), (Ambiente estudio neutro con fondo rosa), (Shadows Dramatic), (Sculpted features), (tez radiante), (Presencia inolvidable), (enigmatic aura), (Sonrisa deslumbrante), (Estilo sofisticado), (fondo neutral limpio), (Confianza sin remordimientos), (Encanto cautivador), (stunning images), (artistic rendition), (Foto de glamour), (attention-grabbing), (Impacto inolvidable), (Hypnotic magnetism), (Belleza poco convencional), (Elegancia atemporal), (Glamour inolvidable), (Vestuario stripper), (estiletto shoes:1), (Carisma irresistible), (Expresiones provocativas), (Sensual appeal), (Fascinating composition), (Retrato inolvidable), (poses sugestivas), (posando sexualmente), (pose erotica), (cuerpo completo:1).", "output": {"url": "images/d436a8829f6ba3081fff0383ec331d6b1547b48d.png"}}, {"text": "La mejor calidad, 4k, 8k, Altas Resoluciones, Obra maestra:1.2, Ultra detallado, realista:1.37, (Cinematographer, cuerpo completo), (Hermosa cara detallada, hermosos ojos detallados, hermosos labios detallados), (Modelo Latina, Milf), (Glamuroso, seductor), (posando en un estudio con luz de estudio), (colores vibrantes, alto contraste), (Soft natural lighting), (Sensual, seductor), (Vestimenta provocativa), (Cabello largo y suelto), (Piel impecable), (photo studio shoot), (mirada caliente), (Postura sexual), (Maquillaje llamativo), (Joyas exquisitas), (Accesorios elegantes), (intense expression), (Belleza cautivadora), (Meticulous Attention to Detail), (Professional Photography), (Striking Composition), (encanto femenino), (Figura de reloj de arena), (Perfectly manicured nails), (Pose erotica), (ojos expresivos), (Curvas deseables), (Ambiente estudio neutro con fondo rosa), (Shadows Dramatic), (Sculpted features), (tez radiante), (Presencia inolvidable), (enigmatic aura), (Sonrisa deslumbrante), (Estilo sofisticado), (fondo neutral limpio), (Confianza sin remordimientos), (Encanto cautivador), (stunning images), (artistic rendition), (Foto de glamour), (attention-grabbing), (Impacto inolvidable), (Hypnotic magnetism), (Belleza poco convencional), (Elegancia atemporal), (Glamour inolvidable), (Vestuario stripper), (estiletto shoes:1), (Carisma irresistible), (Expresiones provocativas), (Sensual appeal), (Fascinating composition), (Retrato inolvidable), (poses sugestivas), (posando sexualmente), (pose erotica), (cuerpo completo:1).", "output": {"url": "images/9ea9ea9fcd1c2802e44e503d58e221811b01a5cf_high.webp"}}], "base_model": "runwayml/stable-diffusion-v1-5", "instance_prompt": "NickyFerrari, MILF, Nicky Ferrari"}

text-to-image

HankMoody1980/NickyFerrari

2023-11-12T08:03:10+00:00

TAGS #diffusers #text-to-image #stable-diffusion #lora #template-sd-lora #base_model-runwayml/stable-diffusion-v1-5 #license-artistic-2.0 #has_space #region-us

# Nicky Ferrari <Gallery /> ## Model description Modelo de Nicky Ferrari ## Trigger words You should use 'NickyFerrari' to trigger the image generation. You should use 'MILF' to trigger the image generation. You should use 'Nicky Ferrari' to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. Download them in the Files & versions tab.

# **Q-Learning** Agent playing1 **FrozenLake-v1** This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** . ## Usage ```python model = load_from_hub(repo_id="youngsterEthan/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```

{"tags": ["FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "q-FrozenLake-v1-4x4-noSlippery", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "FrozenLake-v1-4x4-no_slippery", "type": "FrozenLake-v1-4x4-no_slippery"}, "metrics": [{"type": "mean_reward", "value": "1.00 +/- 0.00", "name": "mean_reward", "verified": false}]}]}]}

reinforcement-learning

youngsterEthan/q-FrozenLake-v1-4x4-noSlippery

2023-11-12T08:09:42+00:00

TAGS #FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us

# Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-fire-detection This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0103 - Precision: 0.9987 - Recall: 0.9987 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:| | 0.0797 | 1.0 | 190 | 0.0811 | 0.9789 | 0.9775 | | 0.0536 | 2.0 | 380 | 0.0205 | 0.9947 | 0.9947 | | 0.0374 | 3.0 | 570 | 0.0283 | 0.9922 | 0.9921 | | 0.0209 | 4.0 | 760 | 0.0046 | 1.0 | 1.0 | | 0.0104 | 5.0 | 950 | 0.0128 | 0.9960 | 0.9960 | | 0.0159 | 6.0 | 1140 | 0.0152 | 0.9947 | 0.9947 | | 0.0119 | 7.0 | 1330 | 0.0084 | 0.9974 | 0.9974 | | 0.0044 | 8.0 | 1520 | 0.0111 | 0.9987 | 0.9987 | | 0.0077 | 9.0 | 1710 | 0.0094 | 0.9987 | 0.9987 | | 0.0106 | 10.0 | 1900 | 0.0103 | 0.9987 | 0.9987 | ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu121 - Tokenizers 0.15.0

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["precision", "recall"], "base_model": "google/vit-base-patch16-224-in21k", "model-index": [{"name": "vit-fire-detection", "results": []}]}

image-classification

Madhukar7559/vit-fire-detection

2023-11-12T08:10:08+00:00

TAGS #transformers #tensorboard #safetensors #vit #image-classification #generated_from_trainer #base_model-google/vit-base-patch16-224-in21k #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us

vit-fire-detection ================== This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set: * Loss: 0.0103 * Precision: 0.9987 * Recall: 0.9987 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0002 * train\_batch\_size: 32 * eval\_batch\_size: 32 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_steps: 100 * num\_epochs: 10 ### Training results ### Framework versions * Transformers 4.35.2 * Pytorch 2.1.0+cu121 * Tokenizers 0.15.0

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-finetuned-clinc This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset. It achieves the following results on the evaluation set: - Loss: 0.7725 - Accuracy: 0.9165 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 48 - eval_batch_size: 48 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 318 | 3.2763 | 0.7284 | | 3.7825 | 2.0 | 636 | 1.8625 | 0.8365 | | 3.7825 | 3.0 | 954 | 1.1513 | 0.8984 | | 1.6859 | 4.0 | 1272 | 0.8540 | 0.9135 | | 0.8984 | 5.0 | 1590 | 0.7725 | 0.9165 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu118 - Datasets 1.16.1 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["clinc_oos"], "metrics": ["accuracy"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "distilbert-base-uncased-finetuned-clinc", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "clinc_oos", "type": "clinc_oos", "config": "plus", "split": "validation", "args": "plus"}, "metrics": [{"type": "accuracy", "value": 0.9164516129032259, "name": "Accuracy"}]}]}]}

text-classification

takaiwai/distilbert-base-uncased-finetuned-clinc

2023-11-12T08:11:16+00:00

TAGS #transformers #tensorboard #safetensors #distilbert #text-classification #generated_from_trainer #dataset-clinc_oos #base_model-distilbert-base-uncased #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us

distilbert-base-uncased-finetuned-clinc ======================================= This model is a fine-tuned version of distilbert-base-uncased on the clinc\_oos dataset. It achieves the following results on the evaluation set: * Loss: 0.7725 * Accuracy: 0.9165 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 2e-05 * train\_batch\_size: 48 * eval\_batch\_size: 48 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * num\_epochs: 5 ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0+cu118 * Datasets 1.16.1 * Tokenizers 0.14.1

# **Q-Learning** Agent playing1 **Taxi-v3** This is a trained model of a **Q-Learning** agent playing **Taxi-v3** . ## Usage ```python model = load_from_hub(repo_id="youngsterEthan/Taxi-v3", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```

{"tags": ["Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "Taxi-v3", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "Taxi-v3", "type": "Taxi-v3"}, "metrics": [{"type": "mean_reward", "value": "7.52 +/- 2.73", "name": "mean_reward", "verified": false}]}]}]}

reinforcement-learning

youngsterEthan/Taxi-v3

2023-11-12T08:12:51+00:00

TAGS #Taxi-v3 #q-learning #reinforcement-learning #custom-implementation #model-index #region-us

# Q-Learning Agent playing1 Taxi-v3 This is a trained model of a Q-Learning agent playing Taxi-v3 . ## Usage

stable-baselines3

# **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

{"library_name": "stable-baselines3", "tags": ["LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "PPO", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "LunarLander-v2", "type": "LunarLander-v2"}, "metrics": [{"type": "mean_reward", "value": "244.81 +/- 15.69", "name": "mean_reward", "verified": false}]}]}]}

reinforcement-learning

Jourllker/ppo-LunarLander-v2

2023-11-12T08:20:01+00:00

TAGS #stable-baselines3 #LunarLander-v2 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us

# PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the stable-baselines3 library. ## Usage (with Stable-baselines3) TODO: Add your code

transformers

fine-tune https://huggingface.co/ai-forever/ruBert-base with dataset toxic messages examples

{"language": ["ru"], "datasets": ["marriamaslova/toxic_dvach_small"]}

text-classification

assskelad/ruBerttox

2023-11-12T08:21:07+00:00

TAGS #transformers #pytorch #bert #text-classification #ru #dataset-marriamaslova/toxic_dvach_small #autotrain_compatible #endpoints_compatible #region-us

fine-tune URL with dataset toxic messages examples

transformers

Made by finetuning [t5-small](https://huggingface.co/t5-small).

{}

text2text-generation

aboli-marathe/t5small_curbest

2023-11-12T08:21:23+00:00

TAGS #transformers #safetensors #t5 #text2text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

Made by finetuning t5-small.

peft

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.6.1 ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.6.1

{"library_name": "peft", "base_model": "vilsonrodrigues/falcon-7b-instruct-sharded"}

XueHaoTay/falcon7b-mental

2023-11-12T08:25:06+00:00

TAGS #peft #arxiv-1910.09700 #base_model-vilsonrodrigues/falcon-7b-instruct-sharded #region-us

# Model Card for Model ID ## Model Details ### Model Description - Developed by: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact ## Training procedure The following 'bitsandbytes' quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.6.1 ## Training procedure The following 'bitsandbytes' quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.6.1

This repo contains fp16, q8_0, and q4_k_m quants of Nethena-20b-Glued, a model that is [NeverSleep/Nethena-20B](https://huggingface.co/NeverSleep/Nethena-20B) with [athirdpath/Nethena-20b-Glue-LORA](https://huggingface.co/athirdpath/Nethena-20b-Glue-LORA) applied. athirdpath/Nethena-20b-Glue-LORA is a 128 rank LORA for RP, trained on NeverSleep/Nethena-20B with a private dataset. It is unalligned and NSFW-oriented. This is a test, exploring the effects of "gluing" the components of the 20b model together to reduce the iconic word replacement errors, increase lucidity, and improve recall.  The private ~500k token dataset used to train the LORA was Alpaca formatted and focused on 4 primary categories: - Medical texts (on psychology, reproductive organs, anatomy, and pregnancy). These are formatted so the model, in character as a doctor or therapist, answers a patient's question in short to medium form. - Excerpts from short stories and novellas (erotic and romantic) centered around both realistic and fantastic situations, covering several fetishes as well. These are sliced into ~2048 token chunks, and these long-form responses are all tied to the command “Enter narrator mode.” in the instructions. - A selection from PIPPA, using a wide keyword search for tokens associated with low quality human or AI data to remove those responses, then a positive search was done for words and phrases associated with a higher reading level. These are converted to Alpaca with “Enter RP mode.” in all the instruction fields. - ~18k tokens of GPT-4 generated data on role-playing from various characters’ perspectives, focusing on different situations and emotions. Includes many multi-turn conversations. So far it is passing subjective testing with flying colors, objective numbers coming soon. Trained with Alpaca-style prompts.

{"license": "cc-by-nc-4.0", "tags": ["not-for-all-audiences"]}

athirdpath/Nethena-20b-Glued-GGUF

2023-11-12T08:27:22+00:00

TAGS #gguf #not-for-all-audiences #license-cc-by-nc-4.0 #region-us

This repo contains fp16, q8_0, and q4_k_m quants of Nethena-20b-Glued, a model that is NeverSleep/Nethena-20B with athirdpath/Nethena-20b-Glue-LORA applied. athirdpath/Nethena-20b-Glue-LORA is a 128 rank LORA for RP, trained on NeverSleep/Nethena-20B with a private dataset. It is unalligned and NSFW-oriented. This is a test, exploring the effects of "gluing" the components of the 20b model together to reduce the iconic word replacement errors, increase lucidity, and improve recall. !image/png The private ~500k token dataset used to train the LORA was Alpaca formatted and focused on 4 primary categories: - Medical texts (on psychology, reproductive organs, anatomy, and pregnancy). These are formatted so the model, in character as a doctor or therapist, answers a patient's question in short to medium form. - Excerpts from short stories and novellas (erotic and romantic) centered around both realistic and fantastic situations, covering several fetishes as well. These are sliced into ~2048 token chunks, and these long-form responses are all tied to the command “Enter narrator mode.” in the instructions. - A selection from PIPPA, using a wide keyword search for tokens associated with low quality human or AI data to remove those responses, then a positive search was done for words and phrases associated with a higher reading level. These are converted to Alpaca with “Enter RP mode.” in all the instruction fields. - ~18k tokens of GPT-4 generated data on role-playing from various characters’ perspectives, focusing on different situations and emotions. Includes many multi-turn conversations. So far it is passing subjective testing with flying colors, objective numbers coming soon. Trained with Alpaca-style prompts.

peft

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.6.2.dev0

{"library_name": "peft", "base_model": "mistralai/Mistral-7B-Instruct-v0.1"}

Prompt48/Mistral-7B-Instruct-v0.1-fine-tuned-adapters-V1

2023-11-12T08:35:05+00:00

TAGS #peft #safetensors #arxiv-1910.09700 #base_model-mistralai/Mistral-7B-Instruct-v0.1 #region-us

# Model Card for Model ID ## Model Details ### Model Description - Developed by: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact ## Training procedure The following 'bitsandbytes' quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.6.2.dev0

transformers

Made by finetuning [t5-small](https://huggingface.co/t5-small).

{}

text2text-generation

aboli-marathe/t5small_10kbest

2023-11-12T08:37:25+00:00

TAGS #transformers #safetensors #t5 #text2text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

Made by finetuning t5-small.

diffusers

### Emma2Ai Dreambooth model trained by melaris with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb) Sample pictures of this concept:

{"license": "creativeml-openrail-m", "tags": ["text-to-image", "stable-diffusion"]}

text-to-image

melaris/emma2ai

2023-11-12T08:43:09+00:00

TAGS #diffusers #safetensors #text-to-image #stable-diffusion #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us

### Emma2Ai Dreambooth model trained by melaris with TheLastBen's fast-DreamBooth notebook Test the concept via A1111 Colab fast-Colab-A1111 Sample pictures of this concept:

diffusers

### Emojis_SD13_2000 Dreambooth model trained by YB23code with [TheLastBen's fast-DreamBooth](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb) notebook Test the concept via A1111 Colab [fast-Colab-A1111](https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast_stable_diffusion_AUTOMATIC1111.ipynb) Sample pictures of this concept:

{"license": "creativeml-openrail-m", "tags": ["text-to-image", "stable-diffusion"]}

text-to-image

YB23code/emojis-sd13-2000

2023-11-12T08:43:26+00:00

TAGS #diffusers #safetensors #text-to-image #stable-diffusion #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us

### Emojis_SD13_2000 Dreambooth model trained by YB23code with TheLastBen's fast-DreamBooth notebook Test the concept via A1111 Colab fast-Colab-A1111 Sample pictures of this concept:

transformers

<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # arieg/bw_spec_cls_4_01_noise_200_confirm This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.0143 - Train Sparse Categorical Accuracy: 1.0 - Validation Loss: 0.0140 - Validation Sparse Categorical Accuracy: 1.0 - Epoch: 19 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'AdamWeightDecay', 'clipnorm': 1.0, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 14400, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01} - training_precision: float32 ### Training results | Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch | |:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:| | 0.6064 | 0.9569 | 0.2224 | 1.0 | 0 | | 0.1543 | 1.0 | 0.1168 | 1.0 | 1 | | 0.0979 | 1.0 | 0.0858 | 1.0 | 2 | | 0.0769 | 1.0 | 0.0709 | 1.0 | 3 | | 0.0647 | 1.0 | 0.0603 | 1.0 | 4 | | 0.0558 | 1.0 | 0.0528 | 1.0 | 5 | | 0.0490 | 1.0 | 0.0465 | 1.0 | 6 | | 0.0434 | 1.0 | 0.0414 | 1.0 | 7 | | 0.0387 | 1.0 | 0.0369 | 1.0 | 8 | | 0.0347 | 1.0 | 0.0332 | 1.0 | 9 | | 0.0312 | 1.0 | 0.0300 | 1.0 | 10 | | 0.0282 | 1.0 | 0.0272 | 1.0 | 11 | | 0.0256 | 1.0 | 0.0248 | 1.0 | 12 | | 0.0234 | 1.0 | 0.0226 | 1.0 | 13 | | 0.0214 | 1.0 | 0.0207 | 1.0 | 14 | | 0.0196 | 1.0 | 0.0190 | 1.0 | 15 | | 0.0181 | 1.0 | 0.0176 | 1.0 | 16 | | 0.0167 | 1.0 | 0.0162 | 1.0 | 17 | | 0.0155 | 1.0 | 0.0150 | 1.0 | 18 | | 0.0143 | 1.0 | 0.0140 | 1.0 | 19 | ### Framework versions - Transformers 4.35.0 - TensorFlow 2.14.0 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_keras_callback"], "base_model": "google/vit-base-patch16-224-in21k", "model-index": [{"name": "arieg/bw_spec_cls_4_01_noise_200_confirm", "results": []}]}

image-classification

arieg/bw_spec_cls_4_01_noise_200_confirm

2023-11-12T08:44:51+00:00

TAGS #transformers #tf #vit #image-classification #generated_from_keras_callback #base_model-google/vit-base-patch16-224-in21k #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us

arieg/bw\_spec\_cls\_4\_01\_noise\_200\_confirm =============================================== This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set: * Train Loss: 0.0143 * Train Sparse Categorical Accuracy: 1.0 * Validation Loss: 0.0140 * Validation Sparse Categorical Accuracy: 1.0 * Epoch: 19 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * optimizer: {'name': 'AdamWeightDecay', 'clipnorm': 1.0, 'learning\_rate': {'module': 'keras.optimizers.schedules', 'class\_name': 'PolynomialDecay', 'config': {'initial\_learning\_rate': 3e-05, 'decay\_steps': 14400, 'end\_learning\_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered\_name': None}, 'decay': 0.0, 'beta\_1': 0.9, 'beta\_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight\_decay\_rate': 0.01} * training\_precision: float32 ### Training results ### Framework versions * Transformers 4.35.0 * TensorFlow 2.14.0 * Datasets 2.14.6 * Tokenizers 0.14.1

transformers

<div align="center"> <img src="./Yi.svg" width="200px"> </div> ## Introduction The **Yi** series models are large language models trained from scratch by developers at [01.AI](https://01.ai/). The first public release contains two bilingual(English/Chinese) base models with the parameter sizes of 6B([`Yi-6B`](https://huggingface.co/01-ai/Yi-6B)) and 34B([`Yi-34B`](https://huggingface.co/01-ai/Yi-34B)). Both of them are trained with 4K sequence length and can be extended to 32K during inference time. The [`Yi-6B-200K`](https://huggingface.co/01-ai/Yi-6B-200K) and [`Yi-34B-200K`](https://huggingface.co/01-ai/Yi-34B-200K) are base model with 200K context length. ## News - 🎯 **2023/11/06**: The base model of [`Yi-6B-200K`](https://huggingface.co/01-ai/Yi-6B-200K) and [`Yi-34B-200K`](https://huggingface.co/01-ai/Yi-34B-200K) with 200K context length. - 🎯 **2023/11/02**: The base model of [`Yi-6B`](https://huggingface.co/01-ai/Yi-6B) and [`Yi-34B`](https://huggingface.co/01-ai/Yi-34B). ## Model Performance | Model | MMLU | CMMLU | C-Eval | GAOKAO | BBH | Common-sense Reasoning | Reading Comprehension | Math & Code | | :------------ | :------: | :------: | :------: | :------: | :------: | :--------------------: | :-------------------: | :---------: | | | 5-shot | 5-shot | 5-shot | 0-shot | 3-shot@1 | - | - | - | | LLaMA2-34B | 62.6 | - | - | - | 44.1 | 69.9 | 68.0 | 26.0 | | LLaMA2-70B | 68.9 | 53.3 | - | 49.8 | 51.2 | 71.9 | 69.4 | 36.8 | | Baichuan2-13B | 59.2 | 62.0 | 58.1 | 54.3 | 48.8 | 64.3 | 62.4 | 23.0 | | Qwen-14B | 66.3 | 71.0 | 72.1 | 62.5 | 53.4 | 73.3 | 72.5 | **39.8** | | Skywork-13B | 62.1 | 61.8 | 60.6 | 68.1 | 41.7 | 72.4 | 61.4 | 24.9 | | InternLM-20B | 62.1 | 59.0 | 58.8 | 45.5 | 52.5 | 78.3 | - | 30.4 | | Aquila-34B | 67.8 | 71.4 | 63.1 | - | - | - | - | - | | Falcon-180B | 70.4 | 58.0 | 57.8 | 59.0 | 54.0 | 77.3 | 68.8 | 34.0 | | Yi-6B | 63.2 | 75.5 | 72.0 | 72.2 | 42.8 | 72.3 | 68.7 | 19.8 | | Yi-6B-200K | 64.0 | 75.3 | 73.5 | 73.9 | 42.0 | 72.0 | 69.1 | 19.0 | | **Yi-34B** | **76.3** | **83.7** | 81.4 | 82.8 | **54.3** | **80.1** | 76.4 | 37.1 | | Yi-34B-200K | 76.1 | 83.6 | **81.9** | **83.4** | 52.7 | 79.7 | **76.6** | 36.3 | While benchmarking open-source models, we have observed a disparity between the results generated by our pipeline and those reported in public sources (e.g. OpenCompass). Upon conducting a more in-depth investigation of this difference, we have discovered that various models may employ different prompts, post-processing strategies, and sampling techniques, potentially resulting in significant variations in the outcomes. Our prompt and post-processing strategy remains consistent with the original benchmark, and greedy decoding is employed during evaluation without any post-processing for the generated content. For scores that were not reported by the original authors (including scores reported with different settings), we try to get results with our pipeline. To evaluate the model's capability extensively, we adopted the methodology outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande, ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ were incorporated to evaluate reading comprehension. CSQA was exclusively tested using a 7-shot setup, while all other tests were conducted with a 0-shot configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1), HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code". Due to technical constraints, we did not test Falcon-180 on QuAC and OBQA; the score is derived by averaging the scores on the remaining tasks. Since the scores for these two tasks are generally lower than the average, we believe that Falcon-180B's performance was not underestimated. ## Usage Please visit our [github repository](https://github.com/01-ai/Yi) for general guidance on how to use this model. ## Disclaimer Although we use data compliance checking algorithms during the training process to ensure the compliance of the trained model to the best of our ability, due to the complexity of the data and the diversity of language model usage scenarios, we cannot guarantee that the model will generate correct and reasonable output in all scenarios. Please be aware that there is still a risk of the model producing problematic outputs. We will not be responsible for any risks and issues resulting from misuse, misguidance, illegal usage, and related misinformation, as well as any associated data security concerns. ## License The Yi series models are fully open for academic research and free commercial usage with permission via applications. All usage must adhere to the [Model License Agreement 2.0](https://huggingface.co/01-ai/Yi-6B-200K/blob/main/LICENSE). To apply for the official commercial license, please contact us ([[email protected]](mailto:[email protected])).

{"license": "other", "license_name": "yi-license", "license_link": "LICENSE"}

text-generation

LoneStriker/Yi-6B-200K-Airo-Claude-Puffin

2023-11-12T08:51:07+00:00

TAGS #transformers #pytorch #Yi #text-generation #custom_code #license-other #autotrain_compatible #has_space #region-us

 Introduction ------------ The Yi series models are large language models trained from scratch by developers at 01.AI. The first public release contains two bilingual(English/Chinese) base models with the parameter sizes of 6B('Yi-6B') and 34B('Yi-34B'). Both of them are trained with 4K sequence length and can be extended to 32K during inference time. The 'Yi-6B-200K' and 'Yi-34B-200K' are base model with 200K context length. News ---- * 2023/11/06: The base model of 'Yi-6B-200K' and 'Yi-34B-200K' with 200K context length. * 2023/11/02: The base model of 'Yi-6B' and 'Yi-34B'. Model Performance ----------------- While benchmarking open-source models, we have observed a disparity between the results generated by our pipeline and those reported in public sources (e.g. OpenCompass). Upon conducting a more in-depth investigation of this difference, we have discovered that various models may employ different prompts, post-processing strategies, and sampling techniques, potentially resulting in significant variations in the outcomes. Our prompt and post-processing strategy remains consistent with the original benchmark, and greedy decoding is employed during evaluation without any post-processing for the generated content. For scores that were not reported by the original authors (including scores reported with different settings), we try to get results with our pipeline. To evaluate the model's capability extensively, we adopted the methodology outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande, ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ were incorporated to evaluate reading comprehension. CSQA was exclusively tested using a 7-shot setup, while all other tests were conducted with a 0-shot configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1), HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code". Due to technical constraints, we did not test Falcon-180 on QuAC and OBQA; the score is derived by averaging the scores on the remaining tasks. Since the scores for these two tasks are generally lower than the average, we believe that Falcon-180B's performance was not underestimated. Usage ----- Please visit our github repository for general guidance on how to use this model. Disclaimer ---------- Although we use data compliance checking algorithms during the training process to ensure the compliance of the trained model to the best of our ability, due to the complexity of the data and the diversity of language model usage scenarios, we cannot guarantee that the model will generate correct and reasonable output in all scenarios. Please be aware that there is still a risk of the model producing problematic outputs. We will not be responsible for any risks and issues resulting from misuse, misguidance, illegal usage, and related misinformation, as well as any associated data security concerns. License ------- The Yi series models are fully open for academic research and free commercial usage with permission via applications. All usage must adhere to the Model License Agreement 2.0. To apply for the official commercial license, please contact us (yi@URL).

transformers

<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # SmartGuy/distilbert_base_uncased_assist This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 3.5619 - Validation Loss: 3.5082 - Epoch: 0 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': -996, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01} - training_precision: mixed_float16 ### Training results | Train Loss | Validation Loss | Epoch | |:----------:|:---------------:|:-----:| | 3.5619 | 3.5082 | 0 | ### Framework versions - Transformers 4.35.0 - TensorFlow 2.14.0 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_keras_callback"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "SmartGuy/distilbert_base_uncased_assist", "results": []}]}

fill-mask

SmartGuy/distilbert_base_uncased_assist

2023-11-12T08:51:53+00:00

TAGS #transformers #tf #distilbert #fill-mask #generated_from_keras_callback #base_model-distilbert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us

SmartGuy/distilbert\_base\_uncased\_assist ========================================== This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set: * Train Loss: 3.5619 * Validation Loss: 3.5082 * Epoch: 0 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * optimizer: {'name': 'AdamWeightDecay', 'learning\_rate': {'module': 'transformers.optimization\_tf', 'class\_name': 'WarmUp', 'config': {'initial\_learning\_rate': 2e-05, 'decay\_schedule\_fn': {'module': 'keras.optimizers.schedules', 'class\_name': 'PolynomialDecay', 'config': {'initial\_learning\_rate': 2e-05, 'decay\_steps': -996, 'end\_learning\_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered\_name': None}, 'warmup\_steps': 1000, 'power': 1.0, 'name': None}, 'registered\_name': 'WarmUp'}, 'decay': 0.0, 'beta\_1': 0.9, 'beta\_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight\_decay\_rate': 0.01} * training\_precision: mixed\_float16 ### Training results ### Framework versions * Transformers 4.35.0 * TensorFlow 2.14.0 * Datasets 2.14.6 * Tokenizers 0.14.1

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # speecht5_finetuned_voxpopuli_nl This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset. It achieves the following results on the evaluation set: - Loss: 0.4586 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 4 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 0.5203 | 4.3 | 1000 | 0.4782 | | 0.4954 | 8.61 | 2000 | 0.4647 | | 0.4929 | 12.91 | 3000 | 0.4615 | | 0.4895 | 17.21 | 4000 | 0.4586 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "mit", "tags": ["generated_from_trainer"], "datasets": ["voxpopuli"], "base_model": "microsoft/speecht5_tts", "model-index": [{"name": "speecht5_finetuned_voxpopuli_nl", "results": []}]}

text-to-audio

rafaelha/speecht5_finetuned_voxpopuli_nl

2023-11-12T08:52:50+00:00

TAGS #transformers #tensorboard #safetensors #speecht5 #text-to-audio #generated_from_trainer #dataset-voxpopuli #base_model-microsoft/speecht5_tts #license-mit #endpoints_compatible #region-us

speecht5\_finetuned\_voxpopuli\_nl ================================== This model is a fine-tuned version of microsoft/speecht5\_tts on the voxpopuli dataset. It achieves the following results on the evaluation set: * Loss: 0.4586 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 1e-05 * train\_batch\_size: 4 * eval\_batch\_size: 2 * seed: 42 * gradient\_accumulation\_steps: 8 * total\_train\_batch\_size: 32 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_steps: 500 * training\_steps: 4000 * mixed\_precision\_training: Native AMP ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0+cu118 * Datasets 2.14.6 * Tokenizers 0.14.1

diffusers

# Elldreth's Stolen Dreams This model with the MoistMixV2VAE baked in. Use 'Elldreth' in the prompt for a stronger effect. Original page: https://civitai.com/models/2540/elldreths-stolendreams-mix Comparison:  (Click for larger) Zoom:  Sample and prompt:  Realistic girl standing. Very cute anime faces, chibi art, flawless, painting by gaston bussiere, charles sillem lidderdale. perfect face, full body, baby, masterpiece, highest quality, Pretty CUTE 1girl, blue eyes, skirt, sweater, highly detailed, GIRL

{"license": "creativeml-openrail-m", "library_name": "diffusers", "tags": ["General Purpose", "Base Model", "Elldreth", "theally", "stable-diffusion", "stable-diffusion-diffusers", "diffusers", "text-to-image"], "pipeline_tag": "text-to-image"}

text-to-image

Yntec/StolenDreams

2023-11-12T08:55:05+00:00

TAGS #diffusers #safetensors #General Purpose #Base Model #Elldreth #theally #stable-diffusion #stable-diffusion-diffusers #text-to-image #license-creativeml-openrail-m #endpoints_compatible #has_space #diffusers-StableDiffusionPipeline #region-us

# Elldreth's Stolen Dreams This model with the MoistMixV2VAE baked in. Use 'Elldreth' in the prompt for a stronger effect. Original page: URL Comparison: !Comparison (Click for larger) Zoom: !Zoom Sample and prompt: !Sample Realistic girl standing. Very cute anime faces, chibi art, flawless, painting by gaston bussiere, charles sillem lidderdale. perfect face, full body, baby, masterpiece, highest quality, Pretty CUTE 1girl, blue eyes, skirt, sweater, highly detailed, GIRL

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # bert-base-uncased-finetuned-wikitext200 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset. It achieves the following results on the evaluation set: - Loss: nan ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 1.2711 | 1.0 | 3350 | 1.2736 | | 1.2374 | 2.0 | 6700 | 1.3894 | | 1.2328 | 3.0 | 10050 | nan | ### Framework versions - Transformers 4.27.1 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.13.3

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "model-index": [{"name": "bert-base-uncased-finetuned-wikitext200", "results": []}]}

fill-mask

AfnanTS/bert-base-uncased-finetuned-wikitext200

2023-11-12T08:55:45+00:00

TAGS #transformers #pytorch #tensorboard #bert #fill-mask #generated_from_trainer #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us

bert-base-uncased-finetuned-wikitext200 ======================================= This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set: * Loss: nan Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 2e-05 * train\_batch\_size: 8 * eval\_batch\_size: 8 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * num\_epochs: 3.0 ### Training results ### Framework versions * Transformers 4.27.1 * Pytorch 2.1.0+cu118 * Datasets 2.14.6 * Tokenizers 0.13.3

peft

## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.4.0

{"library_name": "peft"}

bdsaglam/llama-2-7b-chat-hf-kg-cons

2023-11-12T08:56:38+00:00

TAGS #peft #safetensors #region-us

## Training procedure The following 'bitsandbytes' quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.4.0

transformers

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> Made by finetuning [google/flan-t5-small](https://huggingface.co/google/flan-t5-small).

{"license": "unknown", "metrics": ["bleu"], "pipeline_tag": "translation"}

translation

aboli-marathe/flan_t5_finetuned

2023-11-12T09:02:42+00:00

TAGS #transformers #safetensors #t5 #text2text-generation #translation #license-unknown #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

# Model Card for Model ID Made by finetuning google/flan-t5-small.

diffusers

### Monkey-XZG Dreambooth model trained by Harshitha1 following the "Build your own Gen AI model" session by NxtWave. Project Submission Code: NRI 209 Sample pictures of this concept: .webp)

{"license": "creativeml-openrail-m", "tags": ["NxtWave-GenAI-Webinar", "text-to-image", "stable-diffusion"]}

text-to-image

Harshitha1/monkey-xzg

2023-11-12T09:04:29+00:00

TAGS #diffusers #NxtWave-GenAI-Webinar #text-to-image #stable-diffusion #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us

### Monkey-XZG Dreambooth model trained by Harshitha1 following the "Build your own Gen AI model" session by NxtWave. Project Submission Code: NRI 209 Sample pictures of this concept: !0.webp)

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-finetuned-squad This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset. It achieves the following results on the evaluation set: - Loss: 1.1630 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 1.2304 | 1.0 | 5533 | 1.1579 | | 0.9577 | 2.0 | 11066 | 1.1301 | | 0.7465 | 3.0 | 16599 | 1.1630 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["squad"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "distilbert-base-uncased-finetuned-squad", "results": []}]}

question-answering

MikeSharp01/distilbert-base-uncased-finetuned-squad

2023-11-12T09:05:16+00:00

TAGS #transformers #tensorboard #safetensors #distilbert #question-answering #generated_from_trainer #dataset-squad #base_model-distilbert-base-uncased #license-apache-2.0 #endpoints_compatible #region-us

distilbert-base-uncased-finetuned-squad ======================================= This model is a fine-tuned version of distilbert-base-uncased on the squad dataset. It achieves the following results on the evaluation set: * Loss: 1.1630 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 2e-05 * train\_batch\_size: 16 * eval\_batch\_size: 16 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * num\_epochs: 3 ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0+cu118 * Datasets 2.14.6 * Tokenizers 0.14.1

peft

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.6.2.dev0

{"library_name": "peft", "base_model": "mistralai/Mistral-7B-v0.1"}

Jasper0328/Changbai_Mistral7B_Finetuned

2023-11-12T09:14:13+00:00

TAGS #peft #safetensors #arxiv-1910.09700 #base_model-mistralai/Mistral-7B-v0.1 #region-us

# Model Card for Model ID ## Model Details ### Model Description - Developed by: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact ## Training procedure The following 'bitsandbytes' quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.6.2.dev0

peft

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.2.dev0 ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.2.dev0

{"library_name": "peft", "base_model": "bigscience/bloom-1b1"}

rizkyjun/bloom-1b-finetuned-aings-adapters-chat-1

2023-11-12T09:16:10+00:00

TAGS #peft #tensorboard #safetensors #arxiv-1910.09700 #base_model-bigscience/bloom-1b1 #region-us

# Model Card for Model ID ## Model Details ### Model Description - Developed by: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact ## Training procedure The following 'bitsandbytes' quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.2.dev0 ## Training procedure The following 'bitsandbytes' quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.2.dev0

peft

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.2

{"library_name": "peft", "base_model": "openai/whisper-small"}

juri17/whisper-small-peft-225-1e-3

2023-11-12T09:16:49+00:00

TAGS #peft #safetensors #arxiv-1910.09700 #base_model-openai/whisper-small #region-us

# Model Card for Model ID ## Model Details ### Model Description - Developed by: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact ## Training procedure The following 'bitsandbytes' quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.2

# Model Trained Using AutoTrain

{"tags": ["autotrain", "text-generation"], "widget": [{"text": "I love AutoTrain because "}]}

text-generation

Capstone-lpx/mistral-7b-mj-finetuned_set1

2023-11-12T09:18:00+00:00

TAGS #autotrain #text-generation #region-us

# Model Trained Using AutoTrain

peft

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.2.dev0 ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.2.dev0

{"library_name": "peft", "base_model": "bigscience/bloom-1b1"}

rizkyjun/bloom-1b-finetuned-aings-adapters-chat-2

2023-11-12T09:21:39+00:00

TAGS #peft #tensorboard #safetensors #arxiv-1910.09700 #base_model-bigscience/bloom-1b1 #region-us

# Model Card for Model ID ## Model Details ### Model Description - Developed by: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact ## Training procedure The following 'bitsandbytes' quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.2.dev0 ## Training procedure The following 'bitsandbytes' quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.2.dev0

peft

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.2.dev0 ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.2.dev0

{"library_name": "peft", "base_model": "bigscience/bloom-1b1"}

rizkyjun/bloom-1b-finetuned-aings-adapters-chat-3

2023-11-12T09:23:34+00:00

TAGS #peft #tensorboard #safetensors #arxiv-1910.09700 #base_model-bigscience/bloom-1b1 #region-us

# Model Card for Model ID ## Model Details ### Model Description - Developed by: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact ## Training procedure The following 'bitsandbytes' quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.2.dev0 ## Training procedure The following 'bitsandbytes' quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.6.2.dev0

ml-agents

# **poca** Agent playing **SoccerTwos** This is a trained model of a **poca** agent playing **SoccerTwos** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: JunghwanRo/poca-SoccerTwos 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀

{"library_name": "ml-agents", "tags": ["SoccerTwos", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SoccerTwos"]}

reinforcement-learning

JunghwanRo/poca-SoccerTwos

2023-11-12T09:30:26+00:00

TAGS #ml-agents #tensorboard #onnx #SoccerTwos #deep-reinforcement-learning #reinforcement-learning #ML-Agents-SoccerTwos #region-us

# poca Agent playing SoccerTwos This is a trained model of a poca agent playing SoccerTwos using the Unity ML-Agents Library. ## Usage (with ML-Agents) The Documentation: URL We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your browser: URL - A *longer tutorial* to understand how works ML-Agents: URL ### Resume the training ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to URL 2. Step 1: Find your model_id: JunghwanRo/poca-SoccerTwos 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play

more tags are added in this model<br> the first type of tags that can be recognized ： num1, num2, ..., num33<br> the second type of tags that can be recognized ： moinszero, moinsun, moinsdeux<br> each num* represents a composition<br> moinszero = 2^(-0) = 1.00 = 100% complete<br> moinsun = 2^(-1) = 0.50 = 50% complete<br> moinsdeux = 2^(-2) = 0.25 = 25% complete<br> <br> default settings:<br> ddim 18 512×832 or 832×512<br> hire.fix lantent 832×1344 or 1344×832 with denoi=0.50~0.65<br> cfg 6.5<br> <br> enter QQ group 755638032 if you want to know the latest information<br> entrez le groupe QQ 755638032 si vous souhaitez connaître les dernières informations<br> 最新消息见Q群755638032<br>

{"license": "creativeml-openrail-m"}

cyanelis/moinsv1.25

2023-11-12T09:33:57+00:00

TAGS #license-creativeml-openrail-m #region-us

more tags are added in this model<br> the first type of tags that can be recognized ： num1, num2, ..., num33<br> the second type of tags that can be recognized ： moinszero, moinsun, moinsdeux<br> each num* represents a composition<br> moinszero = 2^(-0) = 1.00 = 100% complete<br> moinsun = 2^(-1) = 0.50 = 50% complete<br> moinsdeux = 2^(-2) = 0.25 = 25% complete<br> <br> default settings:<br> ddim 18 512×832 or 832×512<br> URL lantent 832×1344 or 1344×832 with denoi=0.50~0.65<br> cfg 6.5<br> <br> enter QQ group 755638032 if you want to know the latest information<br> entrez le groupe QQ 755638032 si vous souhaitez connaître les dernières informations<br> 最新消息见Q群755638032<br>

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # pegasus-samsum-adrian This model is a fine-tuned version of [google/pegasus-cnn_dailymail](https://huggingface.co/google/pegasus-cnn_dailymail) on the samsum dataset. It achieves the following results on the evaluation set: - Loss: 1.4854 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 1 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 1.6764 | 0.54 | 500 | 1.4854 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu121 - Datasets 2.14.6 - Tokenizers 0.14.1

{"tags": ["generated_from_trainer"], "datasets": ["samsum"], "base_model": "google/pegasus-cnn_dailymail", "model-index": [{"name": "pegasus-samsum-adrian", "results": []}]}

text2text-generation

ADRIANRICO/pegasus-samsum-adrian

2023-11-12T09:34:20+00:00

TAGS #transformers #tensorboard #safetensors #pegasus #text2text-generation #generated_from_trainer #dataset-samsum #base_model-google/pegasus-cnn_dailymail #autotrain_compatible #endpoints_compatible #region-us

pegasus-samsum-adrian ===================== This model is a fine-tuned version of google/pegasus-cnn\_dailymail on the samsum dataset. It achieves the following results on the evaluation set: * Loss: 1.4854 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 5e-05 * train\_batch\_size: 1 * eval\_batch\_size: 1 * seed: 42 * gradient\_accumulation\_steps: 16 * total\_train\_batch\_size: 16 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_steps: 500 * num\_epochs: 1 ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0+cu121 * Datasets 2.14.6 * Tokenizers 0.14.1

Solve the equation: Your mom is a whore. Your dad have a secret family and is gay. Why is this model even exist?

{}

Lil5971/noimports

2023-11-12T09:38:34+00:00

TAGS #region-us

Solve the equation: Your mom is a whore. Your dad have a secret family and is gay. Why is this model even exist?

diffusers

# IP-Adapter Model Card <div align="center"> [**Project Page**](https://ip-adapter.github.io) **|** [**Paper (ArXiv)**](https://arxiv.org/abs/2308.06721) **|** [**Code**](https://github.com/tencent-ailab/IP-Adapter) </div> --- ## Introduction we present IP-Adapter, an effective and lightweight adapter to achieve image prompt capability for the pre-trained text-to-image diffusion models. An IP-Adapter with only 22M parameters can achieve comparable or even better performance to a fine-tuned image prompt model. IP-Adapter can be generalized not only to other custom models fine-tuned from the same base model, but also to controllable generation using existing controllable tools. Moreover, the image prompt can also work well with the text prompt to accomplish multimodal image generation.  ## Models ### Image Encoder - [models/image_encoder](https://huggingface.co/h94/IP-Adapter/tree/main/models/image_encoder): [OpenCLIP-ViT-H-14](https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K) with 632.08M parameter - [sdxl_models/image_encoder](https://huggingface.co/h94/IP-Adapter/tree/main/sdxl_models/image_encoder): [OpenCLIP-ViT-bigG-14](https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k) with 1844.9M parameter More information can be found [here](https://laion.ai/blog/giant-openclip/) ### IP-Adapter for SD 1.5 - [ip-adapter_sd15.bin](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter_sd15.bin): use global image embedding from OpenCLIP-ViT-H-14 as condition - [ip-adapter_sd15_light.bin](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter_sd15_light.bin): same as ip-adapter_sd15, but more compatible with text prompt - [ip-adapter-plus_sd15.bin](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter-plus_sd15.bin): use patch image embeddings from OpenCLIP-ViT-H-14 as condition, closer to the reference image than ip-adapter_sd15 - [ip-adapter-plus-face_sd15.bin](https://huggingface.co/h94/IP-Adapter/blob/main/models/ip-adapter-plus-face_sd15.bin): same as ip-adapter-plus_sd15, but use cropped face image as condition ### IP-Adapter for SDXL 1.0 - [ip-adapter_sdxl.bin](https://huggingface.co/h94/IP-Adapter/blob/main/sdxl_models/ip-adapter_sdxl.bin): use global image embedding from OpenCLIP-ViT-bigG-14 as condition - [ip-adapter_sdxl_vit-h.bin](https://huggingface.co/h94/IP-Adapter/blob/main/sdxl_models/ip-adapter_sdxl_vit-h.bin): same as ip-adapter_sdxl, but use OpenCLIP-ViT-H-14 - [ip-adapter-plus_sdxl_vit-h.bin](https://huggingface.co/h94/IP-Adapter/blob/main/sdxl_models/ip-adapter-plus_sdxl_vit-h.bin): use patch image embeddings from OpenCLIP-ViT-H-14 as condition, closer to the reference image than ip-adapter_xl and ip-adapter_sdxl_vit-h - [ip-adapter-plus-face_sdxl_vit-h.bin](https://huggingface.co/h94/IP-Adapter/blob/main/sdxl_models/ip-adapter-plus-face_sdxl_vit-h.bin): same as ip-adapter-plus_sdxl_vit-h, but use cropped face image as condition

{"language": ["en"], "license": "apache-2.0", "library_name": "diffusers", "tags": ["text-to-image", "stable-diffusion"]}

text-to-image

BeFrend/IP-Adapter

2023-11-12T09:42:19+00:00

TAGS #diffusers #safetensors #text-to-image #stable-diffusion #en #arxiv-2308.06721 #license-apache-2.0 #region-us

# IP-Adapter Model Card <div align="center"> Project Page | Paper (ArXiv) | Code </div> --- ## Introduction we present IP-Adapter, an effective and lightweight adapter to achieve image prompt capability for the pre-trained text-to-image diffusion models. An IP-Adapter with only 22M parameters can achieve comparable or even better performance to a fine-tuned image prompt model. IP-Adapter can be generalized not only to other custom models fine-tuned from the same base model, but also to controllable generation using existing controllable tools. Moreover, the image prompt can also work well with the text prompt to accomplish multimodal image generation. !arch ## Models ### Image Encoder - models/image_encoder: OpenCLIP-ViT-H-14 with 632.08M parameter - sdxl_models/image_encoder: OpenCLIP-ViT-bigG-14 with 1844.9M parameter More information can be found here ### IP-Adapter for SD 1.5 - ip-adapter_sd15.bin: use global image embedding from OpenCLIP-ViT-H-14 as condition - ip-adapter_sd15_light.bin: same as ip-adapter_sd15, but more compatible with text prompt - ip-adapter-plus_sd15.bin: use patch image embeddings from OpenCLIP-ViT-H-14 as condition, closer to the reference image than ip-adapter_sd15 - ip-adapter-plus-face_sd15.bin: same as ip-adapter-plus_sd15, but use cropped face image as condition ### IP-Adapter for SDXL 1.0 - ip-adapter_sdxl.bin: use global image embedding from OpenCLIP-ViT-bigG-14 as condition - ip-adapter_sdxl_vit-h.bin: same as ip-adapter_sdxl, but use OpenCLIP-ViT-H-14 - ip-adapter-plus_sdxl_vit-h.bin: use patch image embeddings from OpenCLIP-ViT-H-14 as condition, closer to the reference image than ip-adapter_xl and ip-adapter_sdxl_vit-h - ip-adapter-plus-face_sdxl_vit-h.bin: same as ip-adapter-plus_sdxl_vit-h, but use cropped face image as condition

**Dataset Amount**: 06:23 minutes **Steps**: 13.000 **Batch File Size**: 8 **Training Time**: 3.5 hours **Creator**: Grausamkeeit (Me) **Voice Actor**: Konstantin Karasik **Сharacter from**: League of Legends Do not upload this model anywhere without my permission. Private messages are always open so write me and I will reply for sure.

{"language": ["ru"], "license": "cc-by-nc-nd-4.0"}

Grausamkeeit/Braum_RU

2023-11-12T09:45:30+00:00

TAGS #ru #license-cc-by-nc-nd-4.0 #region-us

Dataset Amount: 06:23 minutes Steps: 13.000 Batch File Size: 8 Training Time: 3.5 hours Creator: Grausamkeeit (Me) Voice Actor: Konstantin Karasik Сharacter from: League of Legends Do not upload this model anywhere without my permission. Private messages are always open so write me and I will reply for sure.

peft

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.7.0.dev0 ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.7.0.dev0

{"library_name": "peft", "base_model": "ybelkada/falcon-7b-sharded-bf16"}

SPAL0074/falcon_7b_contextaulizer

2023-11-12T09:48:33+00:00

TAGS #peft #safetensors #arxiv-1910.09700 #base_model-ybelkada/falcon-7b-sharded-bf16 #region-us

# Model Card for Model ID ## Model Details ### Model Description - Developed by: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact ## Training procedure The following 'bitsandbytes' quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.7.0.dev0 ## Training procedure The following 'bitsandbytes' quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.7.0.dev0

transformers

 <a href="https://www.buymeacoffee.com/PulsarAI" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a> # Platypus-Nebula-v2-7B Platypus-Nebula-v2-7B is a merge of [bhenrym14/mistral-7b-platypus-fp16](https://huggingface.co/bhenrym14/mistral-7b-platypus-fp16) and [PulsarAI/Nebula-v2-7B-Lora](https://huggingface.co/PulsarAI/Nebula-v2-7B-Lora) # Evaluation Results ([Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)) | Metric | Value | |-----------------------|-----------| | Avg. | | | ARC (25-shot) | | | HellaSwag (10-shot) | | | MMLU (5-shot) | | | TruthfulQA (0-shot) | | | Winogrande (5-shot) | | | GSM8K (5-shot) | | | DROP (3-shot) | |

{"language": ["en"], "license": "cc-by-nc-4.0", "datasets": ["garage-bAInd/Open-Platypus"]}

text-generation

Weyaxi/Platypus-Nebula-v2-7B

2023-11-12T09:54:38+00:00

TAGS #transformers #safetensors #mistral #text-generation #en #dataset-garage-bAInd/Open-Platypus #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

!image/png <a href="URL target="\_blank"><img src="URL alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" > Platypus-Nebula-v2-7B ===================== Platypus-Nebula-v2-7B is a merge of bhenrym14/mistral-7b-platypus-fp16 and PulsarAI/Nebula-v2-7B-Lora Evaluation Results (Open LLM Leaderboard) =========================================

diffusers

# PicX API Inference  ## Get API Key Get API key from [Stable Diffusion API](http://stablediffusionapi.com/), No Payment needed. Replace Key in below code, change **model_id** to "picx" Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://stablediffusionapi.com/docs) Try model for free: [Generate Images](https://stablediffusionapi.com/models/picx) Model link: [View model](https://stablediffusionapi.com/models/picx) Credits: [View credits](https://civitai.com/?query=PicX) View all models: [View Models](https://stablediffusionapi.com/models) import requests import json url = "https://stablediffusionapi.com/api/v4/dreambooth" payload = json.dumps({ "key": "your_api_key", "model_id": "picx", "prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K", "negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime", "width": "512", "height": "512", "samples": "1", "num_inference_steps": "30", "safety_checker": "no", "enhance_prompt": "yes", "seed": None, "guidance_scale": 7.5, "multi_lingual": "no", "panorama": "no", "self_attention": "no", "upscale": "no", "embeddings": "embeddings_model_id", "lora": "lora_model_id", "webhook": None, "track_id": None }) headers = { 'Content-Type': 'application/json' } response = requests.request("POST", url, headers=headers, data=payload) print(response.text) > Use this coupon code to get 25% off **DMGG0RBN**

{"license": "creativeml-openrail-m", "tags": ["stablediffusionapi.com", "stable-diffusion-api", "text-to-image", "ultra-realistic"], "pinned": true}

text-to-image

stablediffusionapi/picx

2023-11-12T10:03:03+00:00

TAGS #diffusers #stablediffusionapi.com #stable-diffusion-api #text-to-image #ultra-realistic #license-creativeml-openrail-m #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us

# PicX API Inference !generated from URL ## Get API Key Get API key from Stable Diffusion API, No Payment needed. Replace Key in below code, change model_id to "picx" Coding in PHP/Node/Java etc? Have a look at docs for more code examples: View docs Try model for free: Generate Images Model link: View model Credits: View credits View all models: View Models import requests import json url = "URL payload = URL({ "key": "your_api_key", "model_id": "picx", "prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K", "negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime", "width": "512", "height": "512", "samples": "1", "num_inference_steps": "30", "safety_checker": "no", "enhance_prompt": "yes", "seed": None, "guidance_scale": 7.5, "multi_lingual": "no", "panorama": "no", "self_attention": "no", "upscale": "no", "embeddings": "embeddings_model_id", "lora": "lora_model_id", "webhook": None, "track_id": None }) headers = { 'Content-Type': 'application/json' } response = requests.request("POST", url, headers=headers, data=payload) print(URL) > Use this coupon code to get 25% off DMGG0RBN

<div align="center"> <img src="./Yi.svg" width="200px"> </div> ## Introduction The **Yi** series models are large language models trained from scratch by developers at [01.AI](https://01.ai/). The first public release contains two bilingual(English/Chinese) base models with the parameter sizes of 6B([`Yi-6B`](https://huggingface.co/01-ai/Yi-6B)) and 34B([`Yi-34B`](https://huggingface.co/01-ai/Yi-34B)). Both of them are trained with 4K sequence length and can be extended to 32K during inference time. The [`Yi-6B-200K`](https://huggingface.co/01-ai/Yi-6B-200K) and [`Yi-34B-200K`](https://huggingface.co/01-ai/Yi-34B-200K) are base model with 200K context length. ## News - 🎯 **2023/11/06**: The base model of [`Yi-6B-200K`](https://huggingface.co/01-ai/Yi-6B-200K) and [`Yi-34B-200K`](https://huggingface.co/01-ai/Yi-34B-200K) with 200K context length. - 🎯 **2023/11/02**: The base model of [`Yi-6B`](https://huggingface.co/01-ai/Yi-6B) and [`Yi-34B`](https://huggingface.co/01-ai/Yi-34B). ## Model Performance | Model | MMLU | CMMLU | C-Eval | GAOKAO | BBH | Common-sense Reasoning | Reading Comprehension | Math & Code | | :------------ | :------: | :------: | :------: | :------: | :------: | :--------------------: | :-------------------: | :---------: | | | 5-shot | 5-shot | 5-shot | 0-shot | 3-shot@1 | - | - | - | | LLaMA2-34B | 62.6 | - | - | - | 44.1 | 69.9 | 68.0 | 26.0 | | LLaMA2-70B | 68.9 | 53.3 | - | 49.8 | 51.2 | 71.9 | 69.4 | 36.8 | | Baichuan2-13B | 59.2 | 62.0 | 58.1 | 54.3 | 48.8 | 64.3 | 62.4 | 23.0 | | Qwen-14B | 66.3 | 71.0 | 72.1 | 62.5 | 53.4 | 73.3 | 72.5 | **39.8** | | Skywork-13B | 62.1 | 61.8 | 60.6 | 68.1 | 41.7 | 72.4 | 61.4 | 24.9 | | InternLM-20B | 62.1 | 59.0 | 58.8 | 45.5 | 52.5 | 78.3 | - | 30.4 | | Aquila-34B | 67.8 | 71.4 | 63.1 | - | - | - | - | - | | Falcon-180B | 70.4 | 58.0 | 57.8 | 59.0 | 54.0 | 77.3 | 68.8 | 34.0 | | Yi-6B | 63.2 | 75.5 | 72.0 | 72.2 | 42.8 | 72.3 | 68.7 | 19.8 | | Yi-6B-200K | 64.0 | 75.3 | 73.5 | 73.9 | 42.0 | 72.0 | 69.1 | 19.0 | | **Yi-34B** | **76.3** | **83.7** | 81.4 | 82.8 | **54.3** | **80.1** | 76.4 | 37.1 | | Yi-34B-200K | 76.1 | 83.6 | **81.9** | **83.4** | 52.7 | 79.7 | **76.6** | 36.3 | While benchmarking open-source models, we have observed a disparity between the results generated by our pipeline and those reported in public sources (e.g. OpenCompass). Upon conducting a more in-depth investigation of this difference, we have discovered that various models may employ different prompts, post-processing strategies, and sampling techniques, potentially resulting in significant variations in the outcomes. Our prompt and post-processing strategy remains consistent with the original benchmark, and greedy decoding is employed during evaluation without any post-processing for the generated content. For scores that were not reported by the original authors (including scores reported with different settings), we try to get results with our pipeline. To evaluate the model's capability extensively, we adopted the methodology outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande, ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ were incorporated to evaluate reading comprehension. CSQA was exclusively tested using a 7-shot setup, while all other tests were conducted with a 0-shot configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1), HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code". Due to technical constraints, we did not test Falcon-180 on QuAC and OBQA; the score is derived by averaging the scores on the remaining tasks. Since the scores for these two tasks are generally lower than the average, we believe that Falcon-180B's performance was not underestimated. ## Usage Please visit our [github repository](https://github.com/01-ai/Yi) for general guidance on how to use this model. ## Disclaimer Although we use data compliance checking algorithms during the training process to ensure the compliance of the trained model to the best of our ability, due to the complexity of the data and the diversity of language model usage scenarios, we cannot guarantee that the model will generate correct and reasonable output in all scenarios. Please be aware that there is still a risk of the model producing problematic outputs. We will not be responsible for any risks and issues resulting from misuse, misguidance, illegal usage, and related misinformation, as well as any associated data security concerns. ## License The Yi series models are fully open for academic research and free commercial usage with permission via applications. All usage must adhere to the [Model License Agreement 2.0](https://huggingface.co/01-ai/Yi-6B-200K/blob/main/LICENSE). To apply for the official commercial license, please contact us ([[email protected]](mailto:[email protected])).

{"license": "other", "license_name": "yi-license", "license_link": "LICENSE"}

LoneStriker/Yi-6B-200K-Airo-Claude-Puffin-GGUF

2023-11-12T10:04:19+00:00

TAGS #gguf #license-other #region-us

 Introduction ------------ The Yi series models are large language models trained from scratch by developers at 01.AI. The first public release contains two bilingual(English/Chinese) base models with the parameter sizes of 6B('Yi-6B') and 34B('Yi-34B'). Both of them are trained with 4K sequence length and can be extended to 32K during inference time. The 'Yi-6B-200K' and 'Yi-34B-200K' are base model with 200K context length. News ---- * 2023/11/06: The base model of 'Yi-6B-200K' and 'Yi-34B-200K' with 200K context length. * 2023/11/02: The base model of 'Yi-6B' and 'Yi-34B'. Model Performance ----------------- While benchmarking open-source models, we have observed a disparity between the results generated by our pipeline and those reported in public sources (e.g. OpenCompass). Upon conducting a more in-depth investigation of this difference, we have discovered that various models may employ different prompts, post-processing strategies, and sampling techniques, potentially resulting in significant variations in the outcomes. Our prompt and post-processing strategy remains consistent with the original benchmark, and greedy decoding is employed during evaluation without any post-processing for the generated content. For scores that were not reported by the original authors (including scores reported with different settings), we try to get results with our pipeline. To evaluate the model's capability extensively, we adopted the methodology outlined in Llama2. Specifically, we included PIQA, SIQA, HellaSwag, WinoGrande, ARC, OBQA, and CSQA to assess common sense reasoning. SquAD, QuAC, and BoolQ were incorporated to evaluate reading comprehension. CSQA was exclusively tested using a 7-shot setup, while all other tests were conducted with a 0-shot configuration. Additionally, we introduced GSM8K (8-shot@1), MATH (4-shot@1), HumanEval (0-shot@1), and MBPP (3-shot@1) under the category "Math & Code". Due to technical constraints, we did not test Falcon-180 on QuAC and OBQA; the score is derived by averaging the scores on the remaining tasks. Since the scores for these two tasks are generally lower than the average, we believe that Falcon-180B's performance was not underestimated. Usage ----- Please visit our github repository for general guidance on how to use this model. Disclaimer ---------- Although we use data compliance checking algorithms during the training process to ensure the compliance of the trained model to the best of our ability, due to the complexity of the data and the diversity of language model usage scenarios, we cannot guarantee that the model will generate correct and reasonable output in all scenarios. Please be aware that there is still a risk of the model producing problematic outputs. We will not be responsible for any risks and issues resulting from misuse, misguidance, illegal usage, and related misinformation, as well as any associated data security concerns. License ------- The Yi series models are fully open for academic research and free commercial usage with permission via applications. All usage must adhere to the Model License Agreement 2.0. To apply for the official commercial license, please contact us (yi@URL).

Deacon-1b Prompt: ``` ### System: You are an AI assistant. User will give you a task. Your goal is to complete the task as faithfully as you can. While performing the task think step-by-step and justify your steps. ### Instruction: How do you fine tune a large language model? ### Response: ``` NousResearch/Nous-Capybara-3B-V1.9 Prompt: ``` <|im_start|>system You are a helpful AI assistant.<|im_end|> <|im_start|>user How are you<|im_end|> <|im_start|>assistant I am doing well!<|im_end|> ``` jondurbin/airoboros-3b-3p11 ``` [INST] <<SYS>> You are a helpful, unbiased, uncensored assistant. <</SYS>> {prompt} [/INST] ``` GeneZC/MiniChat-3B Prompt: ``` <s> [|User|] Hi 👋 </s>[|Assistant|] ``` llmware/bling-stable-lm-3b-4e1t-v0 Prompt: ``` <human>: {prompt} <bot>: or {{text_passage}} {{question/instruction}} ``` OpenBuddy/openbuddy-stablelm-3b-v13 Prompt: ``` You are a helpful, respectful and honest INTP-T AI Assistant named Buddy. You are talking to a human User. Always answer as helpfully and logically as possible, while being safe. Your answers should not include any harmful, political, religious, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information. You can speak fluently in many languages, for example: English, Chinese. You cannot access the internet, but you have vast knowledge, cutoff: 2021-09. You are trained by OpenBuddy team, (https://openbuddy.ai, https://github.com/OpenBuddy/OpenBuddy), you are based on LLaMA and Falcon transformers model, not related to GPT or OpenAI. User: {History input} Assistant: {History output} User: {Input} Assistant: ``` Dimensity/Dimensity-3B Prompt: ``` ### Human: {prompt} ### Assistant: ``` acrastt/Marx-3B-V3 Prompt: ``` ### HUMAN: {prompt} ### RESPONSE: ``` Open-Orca/Mistral-7B-OpenOrca Prompt: ``` <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ```

{"license": "mit"}

KnutJaegersberg/CPU-LLM-Horde

2023-11-12T10:04:24+00:00

TAGS #gguf #license-mit #region-us

Deacon-1b Prompt: NousResearch/Nous-Capybara-3B-V1.9 Prompt: jondurbin/airoboros-3b-3p11 GeneZC/MiniChat-3B Prompt: llmware/bling-stable-lm-3b-4e1t-v0 Prompt: OpenBuddy/openbuddy-stablelm-3b-v13 Prompt: Dimensity/Dimensity-3B Prompt: acrastt/Marx-3B-V3 Prompt: Open-Orca/Mistral-7B-OpenOrca Prompt:

transformers

# GreekT5 (umt5-small-greeksum) A Greek news summarization model trained on [GreekSum](https://github.com/iakovosevdaimon/GreekSUM). This model is part of a series of models trained as part of our research paper: [Giarelis, N., Mastrokostas, C., & Karacapilidis, N. (2023). GreekT5: A Series of Greek Sequence-to-Sequence Models for News Summarization.](https://arxiv.org/abs/2311.07767) The proposed models were trained and evaluated on the same dataset against [GreekBART](https://arxiv.org/abs/2304.00869). For more information see the evaluation section below. <img src="" width="600"/> ## Training dataset The training dataset of `GreekT5-umt5-small-greeksum` is [GreekSum](https://github.com/iakovosevdaimon/GreekSUM/), which is the first news summarization dataset for the Greek Language. This dataset contains ~151,000 news articles collected from [News24/7](https://www.news247.gr/), belonging to various topics (i.e., society, politics, economy, culture or world news). For more information see: [https://arxiv.org/abs/2304.00869](https://arxiv.org/abs/2304.00869) ## Training configuration We trained `google/umt5-small` [300 million parameters (~1.20 GB)] on the GreekSUM train split using the following parameters: * GPU batch size = 6 * Total training epochs = 10 * AdamW optimizer (e = 1e−8, β1 = 0.9 and β2 = 0.0999) * Learning rate = 3e−4 * Linear weight decay * No warmup steps * 32-bit floating precision * Tokenization * maximum input token length = 1024 * maximum output token length = 128 * padding = ‘max_length’ * truncation = True **Note:** T5-based models use a multi-task architecture, the prefix *‘summarize: ’* was prepended in each training sample. ## Evaluation **Approach**|**ROUGE-1**|**ROUGE-2**|**ROUGE-L**|**BERTScore** ------------|-----------|-----------|-----------|------------- TextRank|18.10|5.76|13.84|68.39 GreekT5 (mt5-small)|14.84|1.68|12.39|72.96 **GreekT5 (umt5-small)**|25.49|12.03|21.32|72.86 GreekT5 (umt5-base)|**26.67**|**13.00**|**22.42**|73.41 GreekBART|17.43|2.44|15.08|**75.89** ### Example code ```python from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, pipeline model_name = 'IMISLab/GreekT5-umt5-small-greeksum' model = AutoModelForSeq2SeqLM.from_pretrained(model_name) tokenizer = AutoTokenizer.from_pretrained(model_name) summarizer = pipeline( 'summarization', device = 'cpu', model = model, tokenizer = tokenizer, max_new_tokens = 128, truncation = True ) text = 'Να πάρει ""ξεκάθαρη"" θέση σε σχέση με τον κίνδυνο μετάδοσης του κορονοϊού από τη Θεία Κοινωνία καλεί την κυβέρνηση και τον Πρωθυπουργό με ανακοίνωσή του τη Δευτέρα ο ΣΥΡΙΖΑ. ""Την ώρα που κλείνουν προληπτικά και ορθώς σχολεία, πανεπιστήμια, γήπεδα και λαμβάνονται ειδικά μέτρα ακόμη και για την ορκωμοσία της νέας Προέδρου της Δημοκρατίας, η Ιερά Σύνοδος της Εκκλησίας της Ελλάδος επιμένει ότι το μυστήριο της Θείας Κοινωνίας δεν εγκυμονεί κινδύνους μετάδοσης του κορονοϊού, καλώντας όμως τις ευπαθείς ομάδες να μείνουν σπίτι τους"", αναφέρει η αξιωματική αντιπολίτευση και συνεχίζει: ""Ωστόσο το πρόβλημα δεν είναι τι λέει η Ιερά Σύνοδος, αλλά τι λέει η Πολιτεία και συγκεκριμένα ο ΕΟΔΥ και το Υπουργείο Υγείας, που έχουν και την αποκλειστική κοινωνική ευθύνη για τη μη εξάπλωση του ιού και την προστασία των πολιτών"". ""Σε άλλες ευρωπαϊκές χώρες με εξίσου μεγάλο σεβασμό στη Χριστιανική πίστη και στο θρησκευτικό συναίσθημα, τα μυστήρια της Εκκλησίας είτε αναστέλλονται είτε τροποποιούν το τελετουργικό τους. Μόνο στη χώρα μας έχουμε το θλιβερό προνόμιο μιας πολιτείας που δεν τολμά να πει το αυτονόητο"", προσθέτει, τονίζοντας ότι ""η κυβέρνηση λοιπόν και το Υπουργείο Υγείας οφείλουν να πάρουν δημόσια μια ξεκάθαρη θέση και να μην θυσιάζουν τη δημόσια Υγεία στο βωμό του πολιτικού κόστους"". ""Συμφωνούν ότι η Θεία Κοινωνία δεν εγκυμονεί κινδύνους μετάδοσης του κορονοϊού; Δεν είναι θέμα ευσέβειας αλλά κοινωνικής ευθύνης. Και με τη Δημόσια υγεία δεν μπορούμε να παίζουμε"", καταλήγει η ανακοίνωση του γραφείου Τύπου του ΣΥΡΙΖΑ. *ΠΩΣ ΜΕΤΑΔΙΔΕΤΑΙ. Χρήσιμος οδηγός για να προστατευθείτε από τον κορονοϊό *ΤΑ ΝΟΣΟΚΟΜΕΙΑ ΑΝΑΦΟΡΑΣ. Ποια θα υποδέχονται τα κρούσματα κορονοϊού στην Ελλάδα. *ΤΑΞΙΔΙΑ. Κορονοϊός και αεροδρόμια: Τι να προσέξετε. *Η ΕΠΙΔΗΜΙΑ ΣΤΟΝ ΠΛΑΝΗΤΗ. Δείτε LIVE χάρτη με την εξέλιξη του κορονοϊού.' output = summarizer('summarize: ' + text) print(output[0]['summary_text']) ``` ## Contact If you have any questions/feedback about the model please e-mail one of the following authors: ``` [email protected] [email protected] [email protected] ``` ## Citation The model has been officially released with the article: [GreekT5: A Series of Greek Sequence-to-Sequence Models for News Summarization](https://arxiv.org/). If you use the model, please cite the following: ``` @misc{giarelis2023greekt5, title={GreekT5: A Series of Greek Sequence-to-Sequence Models for News Summarization}, author={Nikolaos Giarelis and Charalampos Mastrokostas and Nikos Karacapilidis}, year={2023}, eprint={2311.07767}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

{"language": ["el"], "license": "apache-2.0", "metrics": ["bertscore", "rouge"], "pipeline_tag": "summarization", "widget": [{"text": "\u039d\u03b1 \u03c0\u03b1\u0301\u03c1\u03b5\u03b9 \"\"\u03be\u03b5\u03ba\u03b1\u0301\u03b8\u03b1\u03c1\u03b7\"\" \u03b8\u03b5\u0301\u03c3\u03b7 \u03c3\u03b5 \u03c3\u03c7\u03b5\u0301\u03c3\u03b7 \u03bc\u03b5 \u03c4\u03bf\u03bd \u03ba\u03b9\u0301\u03bd\u03b4\u03c5\u03bd\u03bf \u03bc\u03b5\u03c4\u03b1\u0301\u03b4\u03bf\u03c3\u03b7\u03c2 \u03c4\u03bf\u03c5 \u03ba\u03bf\u03c1\u03bf\u03bd\u03bf\u03b9\u0308\u03bf\u03c5\u0301 \u03b1\u03c0\u03bf\u0301 \u03c4\u03b7 \u0398\u03b5\u03b9\u0301\u03b1 \u039a\u03bf\u03b9\u03bd\u03c9\u03bd\u03b9\u0301\u03b1 \u03ba\u03b1\u03bb\u03b5\u03b9\u0301 \u03c4\u03b7\u03bd \u03ba\u03c5\u03b2\u03b5\u0301\u03c1\u03bd\u03b7\u03c3\u03b7 \u03ba\u03b1\u03b9 \u03c4\u03bf\u03bd \u03a0\u03c1\u03c9\u03b8\u03c5\u03c0\u03bf\u03c5\u03c1\u03b3\u03bf\u0301 \u03bc\u03b5 \u03b1\u03bd\u03b1\u03ba\u03bf\u03b9\u0301\u03bd\u03c9\u03c3\u03b7\u0301 \u03c4\u03bf\u03c5 \u03c4\u03b7 \u0394\u03b5\u03c5\u03c4\u03b5\u0301\u03c1\u03b1 \u03bf \u03a3\u03a5\u03a1\u0399\u0396\u0391. \"\"\u03a4\u03b7\u03bd \u03c9\u0301\u03c1\u03b1 \u03c0\u03bf\u03c5 \u03ba\u03bb\u03b5\u03b9\u0301\u03bd\u03bf\u03c5\u03bd \u03c0\u03c1\u03bf\u03bb\u03b7\u03c0\u03c4\u03b9\u03ba\u03b1\u0301 \u03ba\u03b1\u03b9 \u03bf\u03c1\u03b8\u03c9\u0301\u03c2 \u03c3\u03c7\u03bf\u03bb\u03b5\u03b9\u0301\u03b1, \u03c0\u03b1\u03bd\u03b5\u03c0\u03b9\u03c3\u03c4\u03b7\u0301\u03bc\u03b9\u03b1, \u03b3\u03b7\u0301\u03c0\u03b5\u03b4\u03b1 \u03ba\u03b1\u03b9 \u03bb\u03b1\u03bc\u03b2\u03b1\u0301\u03bd\u03bf\u03bd\u03c4\u03b1\u03b9 \u03b5\u03b9\u03b4\u03b9\u03ba\u03b1\u0301 \u03bc\u03b5\u0301\u03c4\u03c1\u03b1 \u03b1\u03ba\u03bf\u0301\u03bc\u03b7 \u03ba\u03b1\u03b9 \u03b3\u03b9\u03b1 \u03c4\u03b7\u03bd \u03bf\u03c1\u03ba\u03c9\u03bc\u03bf\u03c3\u03b9\u0301\u03b1 \u03c4\u03b7\u03c2 \u03bd\u03b5\u0301\u03b1\u03c2 \u03a0\u03c1\u03bf\u03b5\u0301\u03b4\u03c1\u03bf\u03c5 \u03c4\u03b7\u03c2 \u0394\u03b7\u03bc\u03bf\u03ba\u03c1\u03b1\u03c4\u03b9\u0301\u03b1\u03c2, \u03b7 \u0399\u03b5\u03c1\u03b1\u0301 \u03a3\u03c5\u0301\u03bd\u03bf\u03b4\u03bf\u03c2 \u03c4\u03b7\u03c2 \u0395\u03ba\u03ba\u03bb\u03b7\u03c3\u03b9\u0301\u03b1\u03c2 \u03c4\u03b7\u03c2 \u0395\u03bb\u03bb\u03b1\u0301\u03b4\u03bf\u03c2 \u03b5\u03c0\u03b9\u03bc\u03b5\u0301\u03bd\u03b5\u03b9 \u03bf\u0301\u03c4\u03b9 \u03c4\u03bf \u03bc\u03c5\u03c3\u03c4\u03b7\u0301\u03c1\u03b9\u03bf \u03c4\u03b7\u03c2 \u0398\u03b5\u03b9\u0301\u03b1\u03c2 \u039a\u03bf\u03b9\u03bd\u03c9\u03bd\u03b9\u0301\u03b1\u03c2 \u03b4\u03b5\u03bd \u03b5\u03b3\u03ba\u03c5\u03bc\u03bf\u03bd\u03b5\u03b9\u0301 \u03ba\u03b9\u03bd\u03b4\u03c5\u0301\u03bd\u03bf\u03c5\u03c2 \u03bc\u03b5\u03c4\u03b1\u0301\u03b4\u03bf\u03c3\u03b7\u03c2 \u03c4\u03bf\u03c5 \u03ba\u03bf\u03c1\u03bf\u03bd\u03bf\u03b9\u0308\u03bf\u03c5\u0301, \u03ba\u03b1\u03bb\u03c9\u0301\u03bd\u03c4\u03b1\u03c2 \u03bf\u0301\u03bc\u03c9\u03c2 \u03c4\u03b9\u03c2 \u03b5\u03c5\u03c0\u03b1\u03b8\u03b5\u03b9\u0301\u03c2 \u03bf\u03bc\u03b1\u0301\u03b4\u03b5\u03c2 \u03bd\u03b1 \u03bc\u03b5\u03b9\u0301\u03bd\u03bf\u03c5\u03bd \u03c3\u03c0\u03b9\u0301\u03c4\u03b9 \u03c4\u03bf\u03c5\u03c2\"\", \u03b1\u03bd\u03b1\u03c6\u03b5\u0301\u03c1\u03b5\u03b9 \u03b7 \u03b1\u03be\u03b9\u03c9\u03bc\u03b1\u03c4\u03b9\u03ba\u03b7\u0301 \u03b1\u03bd\u03c4\u03b9\u03c0\u03bf\u03bb\u03b9\u0301\u03c4\u03b5\u03c5\u03c3\u03b7 \u03ba\u03b1\u03b9 \u03c3\u03c5\u03bd\u03b5\u03c7\u03b9\u0301\u03b6\u03b5\u03b9: \"\"\u03a9\u03c3\u03c4\u03bf\u0301\u03c3\u03bf \u03c4\u03bf \u03c0\u03c1\u03bf\u0301\u03b2\u03bb\u03b7\u03bc\u03b1 \u03b4\u03b5\u03bd \u03b5\u03b9\u0301\u03bd\u03b1\u03b9 \u03c4\u03b9 \u03bb\u03b5\u0301\u03b5\u03b9 \u03b7 \u0399\u03b5\u03c1\u03b1\u0301 \u03a3\u03c5\u0301\u03bd\u03bf\u03b4\u03bf\u03c2, \u03b1\u03bb\u03bb\u03b1\u0301 \u03c4\u03b9 \u03bb\u03b5\u0301\u03b5\u03b9 \u03b7 \u03a0\u03bf\u03bb\u03b9\u03c4\u03b5\u03b9\u0301\u03b1 \u03ba\u03b1\u03b9 \u03c3\u03c5\u03b3\u03ba\u03b5\u03ba\u03c1\u03b9\u03bc\u03b5\u0301\u03bd\u03b1 \u03bf \u0395\u039f\u0394\u03a5 \u03ba\u03b1\u03b9 \u03c4\u03bf \u03a5\u03c0\u03bf\u03c5\u03c1\u03b3\u03b5\u03b9\u0301\u03bf \u03a5\u03b3\u03b5\u03b9\u0301\u03b1\u03c2, \u03c0\u03bf\u03c5 \u03b5\u0301\u03c7\u03bf\u03c5\u03bd \u03ba\u03b1\u03b9 \u03c4\u03b7\u03bd \u03b1\u03c0\u03bf\u03ba\u03bb\u03b5\u03b9\u03c3\u03c4\u03b9\u03ba\u03b7\u0301 \u03ba\u03bf\u03b9\u03bd\u03c9\u03bd\u03b9\u03ba\u03b7\u0301 \u03b5\u03c5\u03b8\u03c5\u0301\u03bd\u03b7 \u03b3\u03b9\u03b1 \u03c4\u03b7 \u03bc\u03b7 \u03b5\u03be\u03b1\u0301\u03c0\u03bb\u03c9\u03c3\u03b7 \u03c4\u03bf\u03c5 \u03b9\u03bf\u03c5\u0301 \u03ba\u03b1\u03b9 \u03c4\u03b7\u03bd \u03c0\u03c1\u03bf\u03c3\u03c4\u03b1\u03c3\u03b9\u0301\u03b1 \u03c4\u03c9\u03bd \u03c0\u03bf\u03bb\u03b9\u03c4\u03c9\u0301\u03bd\"\". \"\"\u03a3\u03b5 \u03b1\u0301\u03bb\u03bb\u03b5\u03c2 \u03b5\u03c5\u03c1\u03c9\u03c0\u03b1\u03b9\u0308\u03ba\u03b5\u0301\u03c2 \u03c7\u03c9\u0301\u03c1\u03b5\u03c2 \u03bc\u03b5 \u03b5\u03be\u03b9\u0301\u03c3\u03bf\u03c5 \u03bc\u03b5\u03b3\u03b1\u0301\u03bb\u03bf \u03c3\u03b5\u03b2\u03b1\u03c3\u03bc\u03bf\u0301 \u03c3\u03c4\u03b7 \u03a7\u03c1\u03b9\u03c3\u03c4\u03b9\u03b1\u03bd\u03b9\u03ba\u03b7\u0301 \u03c0\u03b9\u0301\u03c3\u03c4\u03b7 \u03ba\u03b1\u03b9 \u03c3\u03c4\u03bf \u03b8\u03c1\u03b7\u03c3\u03ba\u03b5\u03c5\u03c4\u03b9\u03ba\u03bf\u0301 \u03c3\u03c5\u03bd\u03b1\u03b9\u0301\u03c3\u03b8\u03b7\u03bc\u03b1, \u03c4\u03b1 \u03bc\u03c5\u03c3\u03c4\u03b7\u0301\u03c1\u03b9\u03b1 \u03c4\u03b7\u03c2 \u0395\u03ba\u03ba\u03bb\u03b7\u03c3\u03b9\u0301\u03b1\u03c2 \u03b5\u03b9\u0301\u03c4\u03b5 \u03b1\u03bd\u03b1\u03c3\u03c4\u03b5\u0301\u03bb\u03bb\u03bf\u03bd\u03c4\u03b1\u03b9 \u03b5\u03b9\u0301\u03c4\u03b5 \u03c4\u03c1\u03bf\u03c0\u03bf\u03c0\u03bf\u03b9\u03bf\u03c5\u0301\u03bd \u03c4\u03bf \u03c4\u03b5\u03bb\u03b5\u03c4\u03bf\u03c5\u03c1\u03b3\u03b9\u03ba\u03bf\u0301 \u03c4\u03bf\u03c5\u03c2. \u039c\u03bf\u0301\u03bd\u03bf \u03c3\u03c4\u03b7 \u03c7\u03c9\u0301\u03c1\u03b1 \u03bc\u03b1\u03c2 \u03b5\u0301\u03c7\u03bf\u03c5\u03bc\u03b5 \u03c4\u03bf \u03b8\u03bb\u03b9\u03b2\u03b5\u03c1\u03bf\u0301 \u03c0\u03c1\u03bf\u03bd\u03bf\u0301\u03bc\u03b9\u03bf \u03bc\u03b9\u03b1\u03c2 \u03c0\u03bf\u03bb\u03b9\u03c4\u03b5\u03b9\u0301\u03b1\u03c2 \u03c0\u03bf\u03c5 \u03b4\u03b5\u03bd \u03c4\u03bf\u03bb\u03bc\u03b1\u0301 \u03bd\u03b1 \u03c0\u03b5\u03b9 \u03c4\u03bf \u03b1\u03c5\u03c4\u03bf\u03bd\u03bf\u0301\u03b7\u03c4\u03bf\"\", \u03c0\u03c1\u03bf\u03c3\u03b8\u03b5\u0301\u03c4\u03b5\u03b9, \u03c4\u03bf\u03bd\u03b9\u0301\u03b6\u03bf\u03bd\u03c4\u03b1\u03c2 \u03bf\u0301\u03c4\u03b9 \"\"\u03b7 \u03ba\u03c5\u03b2\u03b5\u0301\u03c1\u03bd\u03b7\u03c3\u03b7 \u03bb\u03bf\u03b9\u03c0\u03bf\u0301\u03bd \u03ba\u03b1\u03b9 \u03c4\u03bf \u03a5\u03c0\u03bf\u03c5\u03c1\u03b3\u03b5\u03b9\u0301\u03bf \u03a5\u03b3\u03b5\u03b9\u0301\u03b1\u03c2 \u03bf\u03c6\u03b5\u03b9\u0301\u03bb\u03bf\u03c5\u03bd \u03bd\u03b1 \u03c0\u03b1\u0301\u03c1\u03bf\u03c5\u03bd \u03b4\u03b7\u03bc\u03bf\u0301\u03c3\u03b9\u03b1 \u03bc\u03b9\u03b1 \u03be\u03b5\u03ba\u03b1\u0301\u03b8\u03b1\u03c1\u03b7 \u03b8\u03b5\u0301\u03c3\u03b7 \u03ba\u03b1\u03b9 \u03bd\u03b1 \u03bc\u03b7\u03bd \u03b8\u03c5\u03c3\u03b9\u03b1\u0301\u03b6\u03bf\u03c5\u03bd \u03c4\u03b7 \u03b4\u03b7\u03bc\u03bf\u0301\u03c3\u03b9\u03b1 \u03a5\u03b3\u03b5\u03b9\u0301\u03b1 \u03c3\u03c4\u03bf \u03b2\u03c9\u03bc\u03bf\u0301 \u03c4\u03bf\u03c5 \u03c0\u03bf\u03bb\u03b9\u03c4\u03b9\u03ba\u03bf\u03c5\u0301 \u03ba\u03bf\u0301\u03c3\u03c4\u03bf\u03c5\u03c2\"\". \"\"\u03a3\u03c5\u03bc\u03c6\u03c9\u03bd\u03bf\u03c5\u0301\u03bd \u03bf\u0301\u03c4\u03b9 \u03b7 \u0398\u03b5\u03b9\u0301\u03b1 \u039a\u03bf\u03b9\u03bd\u03c9\u03bd\u03b9\u0301\u03b1 \u03b4\u03b5\u03bd \u03b5\u03b3\u03ba\u03c5\u03bc\u03bf\u03bd\u03b5\u03b9\u0301 \u03ba\u03b9\u03bd\u03b4\u03c5\u0301\u03bd\u03bf\u03c5\u03c2 \u03bc\u03b5\u03c4\u03b1\u0301\u03b4\u03bf\u03c3\u03b7\u03c2 \u03c4\u03bf\u03c5 \u03ba\u03bf\u03c1\u03bf\u03bd\u03bf\u03b9\u0308\u03bf\u03c5\u0301; \u0394\u03b5\u03bd \u03b5\u03b9\u0301\u03bd\u03b1\u03b9 \u03b8\u03b5\u0301\u03bc\u03b1 \u03b5\u03c5\u03c3\u03b5\u0301\u03b2\u03b5\u03b9\u03b1\u03c2 \u03b1\u03bb\u03bb\u03b1\u0301 \u03ba\u03bf\u03b9\u03bd\u03c9\u03bd\u03b9\u03ba\u03b7\u0301\u03c2 \u03b5\u03c5\u03b8\u03c5\u0301\u03bd\u03b7\u03c2. \u039a\u03b1\u03b9 \u03bc\u03b5 \u03c4\u03b7 \u0394\u03b7\u03bc\u03bf\u0301\u03c3\u03b9\u03b1 \u03c5\u03b3\u03b5\u03b9\u0301\u03b1 \u03b4\u03b5\u03bd \u03bc\u03c0\u03bf\u03c1\u03bf\u03c5\u0301\u03bc\u03b5 \u03bd\u03b1 \u03c0\u03b1\u03b9\u0301\u03b6\u03bf\u03c5\u03bc\u03b5\"\", \u03ba\u03b1\u03c4\u03b1\u03bb\u03b7\u0301\u03b3\u03b5\u03b9 \u03b7 \u03b1\u03bd\u03b1\u03ba\u03bf\u03b9\u0301\u03bd\u03c9\u03c3\u03b7 \u03c4\u03bf\u03c5 \u03b3\u03c1\u03b1\u03c6\u03b5\u03b9\u0301\u03bf\u03c5 \u03a4\u03c5\u0301\u03c0\u03bf\u03c5 \u03c4\u03bf\u03c5 \u03a3\u03a5\u03a1\u0399\u0396\u0391. *\u03a0\u03a9\u03a3 \u039c\u0395\u03a4\u0391\u0394\u0399\u0394\u0395\u03a4\u0391\u0399. \u03a7\u03c1\u03b7\u0301\u03c3\u03b9\u03bc\u03bf\u03c2 \u03bf\u03b4\u03b7\u03b3\u03bf\u0301\u03c2 \u03b3\u03b9\u03b1 \u03bd\u03b1 \u03c0\u03c1\u03bf\u03c3\u03c4\u03b1\u03c4\u03b5\u03c5\u03b8\u03b5\u03b9\u0301\u03c4\u03b5 \u03b1\u03c0\u03bf\u0301 \u03c4\u03bf\u03bd \u03ba\u03bf\u03c1\u03bf\u03bd\u03bf\u03b9\u0308\u03bf\u0301 *\u03a4\u0391 \u039d\u039f\u03a3\u039f\u039a\u039f\u039c\u0395\u0399\u0391 \u0391\u039d\u0391\u03a6\u039f\u03a1\u0391\u03a3. \u03a0\u03bf\u03b9\u03b1 \u03b8\u03b1 \u03c5\u03c0\u03bf\u03b4\u03b5\u0301\u03c7\u03bf\u03bd\u03c4\u03b1\u03b9 \u03c4\u03b1 \u03ba\u03c1\u03bf\u03c5\u0301\u03c3\u03bc\u03b1\u03c4\u03b1 \u03ba\u03bf\u03c1\u03bf\u03bd\u03bf\u03b9\u0308\u03bf\u03c5\u0301 \u03c3\u03c4\u03b7\u03bd \u0395\u03bb\u03bb\u03b1\u0301\u03b4\u03b1. *\u03a4\u0391\u039e\u0399\u0394\u0399\u0391. \u039a\u03bf\u03c1\u03bf\u03bd\u03bf\u03b9\u0308\u03bf\u0301\u03c2 \u03ba\u03b1\u03b9 \u03b1\u03b5\u03c1\u03bf\u03b4\u03c1\u03bf\u0301\u03bc\u03b9\u03b1: \u03a4\u03b9 \u03bd\u03b1 \u03c0\u03c1\u03bf\u03c3\u03b5\u0301\u03be\u03b5\u03c4\u03b5. *\u0397 \u0395\u03a0\u0399\u0394\u0397\u039c\u0399\u0391 \u03a3\u03a4\u039f\u039d \u03a0\u039b\u0391\u039d\u0397\u03a4\u0397. \u0394\u03b5\u03b9\u0301\u03c4\u03b5 LIVE \u03c7\u03b1\u0301\u03c1\u03c4\u03b7 \u03bc\u03b5 \u03c4\u03b7\u03bd \u03b5\u03be\u03b5\u0301\u03bb\u03b9\u03be\u03b7 \u03c4\u03bf\u03c5 \u03ba\u03bf\u03c1\u03bf\u03bd\u03bf\u03b9\u0308\u03bf\u03c5\u0301.", "example_title": "Politics"}, {"text": "\u039c\u03b5 \u03b1\u0301\u03c1\u03b8\u03c1\u03bf \u03c4\u03b7\u03c2 \u03bc\u03b5 \u03c4\u03b9\u0301\u03c4\u03bb\u03bf \"\"\u0395\u03c0\u03b9\u03c3\u03c4\u03c1\u03b5\u0301\u03c8\u03c4\u03b5 \u03c3\u03c4\u03b7 \u03b8\u03b5\u03b1\u0301 \u0399\u0301\u03c1\u03b9\u03b4\u03b1 \u03c4\u03bf \u03c3\u03c9\u0301\u03bc\u03b1 \u03c4\u03b7\u03c2\"\", \u03b7 \u03b5\u03c6\u03b7\u03bc\u03b5\u03c1\u03b9\u0301\u03b4\u03b1 Washington Post \u03c4\u03b1\u0301\u03c3\u03c3\u03b5\u03c4\u03b1\u03b9 \u03c5\u03c0\u03b5\u0301\u03c1 \u03c4\u03b7\u03c2 \u03b5\u03c0\u03b9\u03c3\u03c4\u03c1\u03bf\u03c6\u03b7\u0301\u03c2 \u03c4\u03c9\u03bd \u03b3\u03bb\u03c5\u03c0\u03c4\u03c9\u0301\u03bd \u03c4\u03bf\u03c5 \u03a0\u03b1\u03c1\u03b8\u03b5\u03bd\u03c9\u0301\u03bd\u03b1, \u03c3\u03c4\u03b7\u03bd \u0391\u03b8\u03b7\u0301\u03bd\u03b1, \u03c3\u03c4\u03b7\u03bd \u03ba\u03bf\u03b9\u03c4\u03b9\u0301\u03b4\u03b1 \u03c4\u03bf\u03c5 \u03b4\u03c5\u03c4\u03b9\u03ba\u03bf\u03c5\u0301 \u03c0\u03bf\u03bb\u03b9\u03c4\u03b9\u03c3\u03bc\u03bf\u03c5\u0301, \u03c4\u03c9\u0301\u03c1\u03b1 \u03c0\u03bf\u03c5 \u03bf\u03b9 \u03c3\u03c5\u03bd\u03b8\u03b7\u0301\u03ba\u03b5\u03c2 \u03b5\u0301\u03c7\u03bf\u03c5\u03bd \u03b1\u03bb\u03bb\u03b1\u0301\u03be\u03b5\u03b9 \u03b3\u03b9\u03b1 \u03c4\u03b7\u03bd \u03c0\u03b1\u0301\u03bb\u03b1\u03b9 \u03c0\u03bf\u03c4\u03b5\u0301 \u03b1\u03c5\u03c4\u03bf\u03ba\u03c1\u03b1\u03c4\u03bf\u03c1\u03b9\u0301\u03b1 \u03c4\u03b7\u03c2 \u0391\u03b3\u03b3\u03bb\u03b9\u0301\u03b1\u03c2. \u0391\u03bd\u03b1\u03c6\u03b5\u03c1\u03bf\u0301\u03bc\u03b5\u03bd\u03b7 \u03c3\u03c4\u03b9\u03c2 \u03b4\u03b9\u03b1\u03c6\u03bf\u03c1\u03b5\u03c4\u03b9\u03ba\u03b5\u0301\u03c2 \u03b1\u03c0\u03bf\u0301\u03c8\u03b5\u03b9\u03c2 \u0395\u03bb\u03bb\u03b7\u0301\u03bd\u03c9\u03bd \u03ba\u03b1\u03b9 \u0392\u03c1\u03b5\u03c4\u03b1\u03bd\u03c9\u0301\u03bd \u03b3\u03b9\u03b1 \u03c4\u03b1 \u03b3\u03bb\u03c5\u03c0\u03c4\u03b1\u0301, \u03b7 \u03c3\u03c5\u03bd\u03c4\u03b1\u0301\u03ba\u03c4\u03c1\u03b9\u03b1 \u03c4\u03bf\u03c5 \u03b1\u0301\u03c1\u03b8\u03c1\u03bf\u03c5, \u03c4\u03bf\u03bd\u03b9\u0301\u03b6\u03b5\u03b9 \u03bf\u0301\u03c4\u03b9 \u03c4\u03bf \u03b1\u03b9\u0301\u03c4\u03b7\u03bc\u03b1 \u03b5\u03c0\u03b9\u03c3\u03c4\u03c1\u03bf\u03c6\u03b7\u0301\u03c2 \u03b5\u0301\u03c7\u03b5\u03b9 \u03b1\u03c0\u03bf\u03ba\u03c4\u03b7\u0301\u03c3\u03b5\u03b9 \u03bc\u03b5\u03b3\u03b1\u03bb\u03c5\u0301\u03c4\u03b5\u03c1\u03bf \u03b2\u03b1\u0301\u03c1\u03bf\u03c2 \u03c4\u03c9\u0301\u03c1\u03b1 \u03c0\u03bf\u03c5 \u03c4\u03bf \u0397\u03bd\u03c9\u03bc\u03b5\u0301\u03bd\u03bf \u0392\u03b1\u03c3\u03b9\u0301\u03bb\u03b5\u03b9\u03bf \u03b5\u03b3\u03ba\u03b1\u03c4\u03b1\u03bb\u03b5\u03b9\u0301\u03c0\u03b5\u03b9 \u03c4\u03b7\u03bd \u0395\u03c5\u03c1\u03c9\u03c0\u03b1\u03b9\u0308\u03ba\u03b7\u0301 \u0395\u0301\u03bd\u03c9\u03c3\u03b7. \u00ab\u039f\u0301\u03c4\u03b1\u03bd \u03bf \u03a4\u03bf\u0301\u03bc\u03b1\u03c2 \u039c\u03c0\u03c1\u03bf\u03c5\u03c2, \u03b5\u0301\u03b2\u03b4\u03bf\u03bc\u03bf\u03c2 \u03ba\u03bf\u0301\u03bc\u03b7\u03c2 \u03c4\u03bf\u03c5 \u0395\u0301\u03bb\u03b3\u03b9\u03bd, \u03ba\u03b1\u03b9 11\u03bf\u03c2 \u03ba\u03bf\u0301\u03bc\u03b7\u03c2 \u03c4\u03bf\u03c5 \u039a\u03b9\u03bd\u03ba\u03b1\u03c1\u03bd\u03c4\u03b9\u0301\u03bd, \u03c4\u03b1\u03be\u03b9\u0301\u03b4\u03b5\u03c8\u03b5 \u03c3\u03c4\u03b7\u03bd \u0391\u03ba\u03c1\u03bf\u0301\u03c0\u03bf\u03bb\u03b7 \u03c3\u03c4\u03b9\u03c2 \u03b1\u03c1\u03c7\u03b5\u0301\u03c2 \u03c4\u03b7\u03c2 \u03b4\u03b5\u03ba\u03b1\u03b5\u03c4\u03b9\u0301\u03b1\u03c2 \u03c4\u03bf\u03c5 1800, \u03c9\u03c2 \u0392\u03c1\u03b5\u03c4\u03b1\u03bd\u03bf\u0301\u03c2 \u03c0\u03c1\u03b5\u0301\u03c3\u03b2\u03b7\u03c2 \u03c3\u03c4\u03b7\u03bd \u039f\u03b8\u03c9\u03bc\u03b1\u03bd\u03b9\u03ba\u03b7\u0301 \u0391\u03c5\u03c4\u03bf\u03ba\u03c1\u03b1\u03c4\u03bf\u03c1\u03b9\u0301\u03b1, \u03bf \u03a3\u03bf\u03c5\u03bb\u03c4\u03b1\u0301\u03bd\u03bf\u03c2 \u03bb\u03b5\u0301\u03b3\u03b5\u03c4\u03b1\u03b9 \u03bf\u0301\u03c4\u03b9 \u03c4\u03bf\u03c5 \u03b5\u0301\u03b4\u03c9\u03c3\u03b5 \u03c4\u03b7\u03bd \u03b1\u0301\u03b4\u03b5\u03b9\u03b1 \u03bd\u03b1 \"\"\u03b1\u03c6\u03b1\u03b9\u03c1\u03b5\u0301\u03c3\u03b5\u03b9 \u03bc\u03b5\u03c1\u03b9\u03ba\u03b1\u0301 \u03c4\u03bc\u03b7\u0301\u03bc\u03b1\u03c4\u03b1 \u03bb\u03b9\u0301\u03b8\u03c9\u03bd \u03bc\u03b5 \u03c0\u03b1\u03bb\u03b9\u03b5\u0301\u03c2 \u03b5\u03c0\u03b9\u03b3\u03c1\u03b1\u03c6\u03b5\u0301\u03c2 \u03ba\u03b1\u03b9 \u03bc\u03bf\u03c1\u03c6\u03b5\u0301\u03c2\"\". \u039f \u03bb\u03bf\u0301\u03c1\u03b4\u03bf\u03c2 \u03c4\u03bf \u03b5\u03be\u03b5\u0301\u03bb\u03b1\u03b2\u03b5 \u03c9\u03c2 \u03b1\u0301\u03b4\u03b5\u03b9\u03b1 \u03bd\u03b1 \u03b1\u03c6\u03b1\u03b9\u03c1\u03b5\u0301\u03c3\u03b5\u03b9, \u03c0\u03b5\u03c1\u03b9\u0301\u03c0\u03bf\u03c5, 17 \u03b1\u03b3\u03b1\u0301\u03bb\u03bc\u03b1\u03c4\u03b1 \u03b1\u03c0\u03bf\u0301 \u03c4\u03b1 \u03b1\u03b5\u03c4\u03c9\u0301\u03bc\u03b1\u03c4\u03b1, 15 \u03bc\u03b5\u03c4\u03c9\u0301\u03c0\u03b5\u03c2, \u03ba\u03b1\u03b9 247 \u03c0\u03bf\u0301\u03b4\u03b9\u03b1 (\u03c0\u03b5\u03c1\u03b9\u0301\u03c0\u03bf\u03c5 75 \u03bc\u03b5\u0301\u03c4\u03c1\u03b1) \u03c4\u03b7\u03c2 \u03b6\u03c9\u03c6\u03bf\u0301\u03c1\u03bf\u03c5 \u03b1\u03c0\u03bf\u0301 \u03c4\u03bf\u03bd \u03a0\u03b1\u03c1\u03b8\u03b5\u03bd\u03c9\u0301\u03bd\u03b1 \u03b3\u03b9\u03b1 \u03bd\u03b1 \u03c4\u03b1 \u03c6\u03b5\u0301\u03c1\u03b5\u03b9 \u03c3\u03c4\u03b7\u03bd \u03ba\u03b1\u03bb\u03b7\u0301 \u03bc\u03b1\u03c2 \u0391\u03b3\u03b3\u03bb\u03b9\u0301\u03b1\u00bb \u03b1\u03bd\u03b1\u03c6\u03b5\u0301\u03c1\u03b5\u03b9 \u03c3\u03c4\u03bf \u03b1\u0301\u03c1\u03b8\u03c1\u03bf \u03c4\u03b7\u03c2 \u03b7 Washington Post. \u039a\u03b1\u03b9 \u03c3\u03c5\u03bd\u03b5\u03c7\u03b9\u0301\u03b6\u03b5\u03b9 \u03bb\u03b5\u0301\u03b3\u03bf\u03bd\u03c4\u03b1\u03c2 \u03bf\u0301\u03c4\u03b9 \u00ab\u03bf\u03b9 \u03ba\u03b1\u03b9\u03c1\u03bf\u03b9\u0301 \u03bf\u0301\u03bc\u03c9\u03c2 \u03b1\u0301\u03bb\u03bb\u03b1\u03be\u03b1\u03bd \u03ba\u03b1\u03b9 \u03b1\u03c5\u03c4\u03bf\u0301 \u03c0\u03bf\u03c5 \u03b8\u03b5\u03c9\u03c1\u03bf\u03c5\u0301\u03bd\u03c4\u03b1\u03bd \u03c0\u03b9\u03bf \u03b4\u03b9\u03ba\u03b1\u03b9\u03bf\u03bb\u03bf\u03b3\u03b7\u03bc\u03b5\u0301\u03bd\u03bf \u03c4\u03bf\u0301\u03c4\u03b5, \u03c3\u03b7\u0301\u03bc\u03b5\u03c1\u03b1 \u03b8\u03b5\u03c9\u03c1\u03b5\u03b9\u0301\u03c4\u03b1\u03b9 \u03b5\u03c5\u03c1\u03b5\u0301\u03c9\u03c2 \u03c9\u03c2 \u03bc\u03b9\u03b1 \u03b1\u03c3\u03c5\u03bd\u03b5\u03b9\u0301\u03b4\u03b7\u03c4\u03b7 \u03c0\u03c1\u03b1\u0301\u03be\u03b7\u00bb. \u03a3\u03b5 \u03bc\u03b9\u0301\u03b1 \u03b5\u0301\u03bc\u03bc\u03b5\u03c3\u03b7 \u03b1\u03bd\u03b1\u03c6\u03bf\u03c1\u03b1\u0301 \u03c3\u03c4\u03bf Brexit, \u03ba\u03b1\u03b9 \u03c5\u03c0\u03b5\u03c1\u03b1\u03bc\u03c5\u03bd\u03bf\u0301\u03bc\u03b5\u03bd\u03b7 \u03c4\u03b7\u03c2 \u03b5\u03c0\u03b9\u03c3\u03c4\u03c1\u03bf\u03c6\u03b7\u0301\u03c2 \u03c4\u03c9\u03bd \u03b3\u03bb\u03c5\u03c0\u03c4\u03c9\u0301\u03bd \u03c3\u03c4\u03b7\u03bd \u0395\u03bb\u03bb\u03b1\u0301\u03b4\u03b1, \u03b7 \u03c3\u03c5\u03bd\u03c4\u03b1\u0301\u03ba\u03c4\u03c1\u03b9\u03b1 \u03c4\u03bf\u03c5 \u03b1\u0301\u03c1\u03b8\u03c1\u03bf\u03c5 \u03c4\u03b7\u03c2 Washington Post, \u03b4\u03b9\u03b5\u03c1\u03c9\u03c4\u03b1\u0301\u03c4\u03b1\u03b9: \u00ab\u0393\u03b9\u03b1\u03c4\u03b9\u0301 \u03bd\u03b1 \u03c0\u03b1\u03c1\u03b1\u03bc\u03b5\u03b9\u0301\u03bd\u03bf\u03c5\u03bd \u03c4\u03b1 \u03bc\u03b1\u0301\u03c1\u03bc\u03b1\u03c1\u03b1 \u03c3\u03c4\u03b7 \u03c6\u03c5\u0301\u03bb\u03b1\u03be\u03b7 \u03c4\u03b7\u03c2 \u03c7\u03c9\u0301\u03c1\u03b1\u03c2 \u03c0\u03bf\u03c5 \u03b5\u03c0\u03b9\u03bc\u03b5\u0301\u03bd\u03b5\u03b9 \u03bf\u0301\u03c4\u03b9 \u03b1\u03bd\u03b7\u0301\u03ba\u03b5\u03b9 \u03bc\u03bf\u0301\u03bd\u03bf \u03c3\u03c4\u03bf\u03bd \u03b5\u03b1\u03c5\u03c4\u03bf\u0301 \u03c4\u03b7\u03c2;\u00bb \u03ba\u03b1\u03b9 \u03c3\u03b7\u03bc\u03b5\u03b9\u03c9\u0301\u03bd\u03b5\u03b9: \u00ab\u0397 \u0395\u03bb\u03bb\u03b1\u0301\u03b4\u03b1 \u03c4\u03b9\u03bc\u03b1\u0301\u03c4\u03b1\u03b9 \u03c3\u03b7\u0301\u03bc\u03b5\u03c1\u03b1 \u03c9\u03c2 \u03bb\u03b9\u0301\u03ba\u03bd\u03bf \u03c4\u03bf\u03c5 \u03b4\u03c5\u03c4\u03b9\u03ba\u03bf\u03c5\u0301 \u03c0\u03bf\u03bb\u03b9\u03c4\u03b9\u03c3\u03bc\u03bf\u03c5\u0301, \u03ba\u03b1\u03b9 \u03c0\u03bf\u03b9\u03bf\u03b9\u0301 \u03c0\u03b1\u03c1\u03b1\u0301 \u03bf\u03b9 \u0395\u0301\u03bb\u03bb\u03b7\u03bd\u03b5\u03c2 \u03b8\u03b1 \u03bc\u03c0\u03bf\u03c1\u03bf\u03c5\u0301\u03c3\u03b1\u03bd \u03bd\u03b1 \u03c3\u03c4\u03b5\u03b3\u03b1\u0301\u03c3\u03bf\u03c5\u03bd \u03c4\u03bf\u03bd \u03c0\u03bf\u03bb\u03b9\u03c4\u03b9\u03c3\u03bc\u03bf\u0301 \u03b1\u03c5\u03c4\u03bf\u0301;\u00bb.", "example_title": "Culture"}, {"text": "\u03a4\u03bf \u0394\u03b9\u03b5\u03b8\u03bd\u03b5\u0301\u03c2 \u039d\u03bf\u03bc\u03b9\u03c3\u03bc\u03b1\u03c4\u03b9\u03ba\u03bf\u0301 \u03a4\u03b1\u03bc\u03b5\u03b9\u0301\u03bf (\u0394\u039d\u03a4) \u03c0\u03c1\u03bf\u03b2\u03bb\u03b5\u0301\u03c0\u03b5\u03b9 \u03b5\u0301\u03bd\u03b1 \u03c7\u03c1\u03b5\u0301\u03bf\u03c2 \u03c1\u03b5\u03ba\u03bf\u0301\u03c1 \u03c4\u03c9\u03bd \u03c0\u03bb\u03bf\u03c5\u0301\u03c3\u03b9\u03c9\u03bd \u03c7\u03c9\u03c1\u03c9\u0301\u03bd \u03c4\u03bf 2014 \u03ba\u03b1\u03b9 \u03ba\u03c1\u03b9\u0301\u03bd\u03b5\u03b9 \"\"\u03c0\u03b9\u03b8\u03b1\u03bd\u03bf\u0301\"\" \u03bd\u03b1 \u03c5\u03c0\u03b1\u0301\u03c1\u03be\u03b5\u03b9 \u03b5\u03c0\u03b9\u03c0\u03bb\u03b5\u0301\u03bf\u03bd \u03c3\u03c5\u03bc\u03b2\u03bf\u03bb\u03b7\u0301 \u03c4\u03c9\u03bd \u03c0\u03b9\u03bf \u03b5\u03c5\u0301\u03c0\u03bf\u03c1\u03c9\u03bd \u03c0\u03c1\u03bf\u03c3\u03c9\u0301\u03c0\u03c9\u03bd \u03ba\u03b1\u03b9 \u03c4\u03c9\u03bd \u03c0\u03bf\u03bb\u03c5\u03b5\u03b8\u03bd\u03b9\u03ba\u03c9\u0301\u03bd \u03b5\u03c0\u03b9\u03c7\u03b5\u03b9\u03c1\u03b7\u0301\u03c3\u03b5\u03c9\u03bd \u03c3\u03b5 \u03bc\u03b9\u03b1 \u03bc\u03b5\u03b9\u0301\u03c9\u03c3\u03b7 \u03c4\u03c9\u03bd \u03b5\u03bb\u03bb\u03b5\u03b9\u03bc\u03bc\u03b1\u0301\u03c4\u03c9\u03bd, \u03c3\u03c5\u0301\u03bc\u03c6\u03c9\u03bd\u03b1 \u03bc\u03b5 \u03b5\u0301\u03ba\u03b8\u03b5\u03c3\u03b7\u0301 \u03c4\u03bf\u03c5 \u03b7 \u03bf\u03c0\u03bf\u03b9\u0301\u03b1 \u03b4\u03bf\u0301\u03b8\u03b7\u03ba\u03b5 \u03c3\u03b7\u0301\u03bc\u03b5\u03c1\u03b1 \u03c3\u03c4\u03b7 \u03b4\u03b7\u03bc\u03bf\u03c3\u03b9\u03bf\u0301\u03c4\u03b7\u03c4\u03b1. \"\"\u03a6\u03b1\u03b9\u0301\u03bd\u03b5\u03c4\u03b1\u03b9 \u03bf\u0301\u03c4\u03b9 \u03c5\u03c0\u03b1\u0301\u03c1\u03c7\u03b5\u03b9 \u03b5\u0301\u03bd\u03b1 \u03b5\u03c0\u03b1\u03c1\u03ba\u03b5\u0301\u03c2 \u03c0\u03b5\u03c1\u03b9\u03b8\u03c9\u0301\u03c1\u03b9\u03bf \u03c3\u03b5 \u03c0\u03bf\u03bb\u03bb\u03b5\u0301\u03c2 \u03b1\u03bd\u03b5\u03c0\u03c4\u03c5\u03b3\u03bc\u03b5\u0301\u03bd\u03b5\u03c2 \u03c7\u03c9\u0301\u03c1\u03b5\u03c2 \u03b3\u03b9\u03b1 \u03bd\u03b1 \u03b1\u03bd\u03c4\u03bb\u03b7\u03b8\u03bf\u03c5\u0301\u03bd \u03b5\u03c0\u03b9\u03c0\u03bb\u03b5\u0301\u03bf\u03bd \u03b5\u0301\u03c3\u03bf\u03b4\u03b1 \u03b1\u03c0\u03bf\u0301 \u03c4\u03b1 \u03c0\u03b9\u03bf \u03c5\u03c8\u03b7\u03bb\u03b1\u0301 \u03b5\u03b9\u03c3\u03bf\u03b4\u03b7\u0301\u03bc\u03b1\u03c4\u03b1\"\", \u03c5\u03c0\u03bf\u03b3\u03c1\u03b1\u03bc\u03bc\u03b9\u0301\u03b6\u03b5\u03b9 \u03c4\u03bf \u0394\u039d\u03a4 \u03c3\u03c4\u03b7\u03bd \u03b5\u0301\u03ba\u03b8\u03b5\u03c3\u03b7\u0301 \u03c4\u03bf\u03c5 \u03b3\u03b9\u03b1 \u03c4\u03b7\u03bd \u03b4\u03b7\u03bc\u03bf\u03c3\u03b9\u03bf\u03bd\u03bf\u03bc\u03b9\u03ba\u03b7\u0301 \u03b5\u03c0\u03b9\u03c4\u03b7\u0301\u03c1\u03b7\u03c3\u03b7. \u039a\u03b1\u03c4\u03b1\u0301 \u03bc\u03b5\u0301\u03c3\u03bf\u03bd \u03bf\u0301\u03c1\u03bf, \u03c4\u03bf \u03b4\u03b7\u03bc\u03bf\u0301\u03c3\u03b9\u03bf \u03c7\u03c1\u03b5\u0301\u03bf\u03c2 \u03c4\u03c9\u03bd \u03b1\u03bd\u03b5\u03c0\u03c4\u03c5\u03b3\u03bc\u03b5\u0301\u03bd\u03c9\u03bd \u03c7\u03c9\u03c1\u03c9\u0301\u03bd \u03b1\u03bd\u03b1\u03bc\u03b5\u0301\u03bd\u03b5\u03c4\u03b1\u03b9 \u03bd\u03b1 \u03c6\u03c4\u03b1\u0301\u03c3\u03b5\u03b9 \u03c4\u03bf \"\"\u03b9\u03c3\u03c4\u03bf\u03c1\u03b9\u03ba\u03bf\u0301 \u03c5\u03c8\u03b7\u03bb\u03bf\u0301\"\" \u03c4\u03bf\u03c5 110% \u03c4\u03bf\u03c5 \u0391\u0395\u03a0 \u03c4\u03bf\u03c5\u03c2 \u03c4\u03bf 2014, \u03b4\u03b7\u03bb\u03b1\u03b4\u03b7\u0301 \u03b8\u03b1 \u03b2\u03c1\u03b9\u0301\u03c3\u03ba\u03b5\u03c4\u03b1\u03b9 35 \u03bc\u03bf\u03bd\u03b1\u0301\u03b4\u03b5\u03c2 \u03c0\u03b9\u03bf \u03c0\u03b1\u0301\u03bd\u03c9 \u03b1\u03c0\u03bf\u0301 \u03c4\u03bf \u03c0\u03bf\u03c3\u03bf\u03c3\u03c4\u03bf\u0301 \u03c4\u03bf\u03c5 2007, \u03b5\u03c0\u03b9\u03c3\u03b7\u03bc\u03b1\u03b9\u0301\u03bd\u03b5\u03b9 \u03c4\u03bf \u0394\u039d\u03a4 \u03c3\u03c4\u03b7\u03bd \u03b5\u0301\u03ba\u03b8\u03b5\u03c3\u03b7\u0301 \u03c4\u03bf\u03c5. \u039c\u03b5 \u03bc\u03b9\u03b1 \u03b1\u03bd\u03b1\u03bb\u03bf\u03b3\u03b9\u0301\u03b1 \u03c7\u03c1\u03b5\u0301\u03bf\u03c5\u03c2/\u0391\u0395\u03a0 \u03c4\u03b7\u03c2 \u03c4\u03b1\u0301\u03be\u03b7\u03c2 \u03c4\u03bf\u03c5 242,3% \u03c0\u03bf\u03c5 \u03c0\u03c1\u03bf\u03b2\u03bb\u03b5\u0301\u03c0\u03b5\u03c4\u03b1\u03b9 \u03bd\u03b1 \u03b5\u0301\u03c7\u03b5\u03b9 \u03c4\u03bf 2014, \u03b7 \u0399\u03b1\u03c0\u03c9\u03bd\u03b9\u0301\u03b1 \u03b1\u03bd\u03b1\u03bc\u03b5\u0301\u03bd\u03b5\u03c4\u03b1\u03b9 \u03bd\u03b1 \u03b2\u03c1\u03b9\u0301\u03c3\u03ba\u03b5\u03c4\u03b1\u03b9 \u03c0\u03c1\u03c9\u0301\u03c4\u03b7 \u03c3\u03c4\u03bf\u03bd \u03ba\u03b1\u03c4\u03b1\u0301\u03bb\u03bf\u03b3\u03bf \u03c4\u03c9\u03bd \u03c5\u03c0\u03b5\u03c1\u03c7\u03c1\u03b5\u03c9\u03bc\u03b5\u0301\u03bd\u03c9\u03bd \u03b1\u03bd\u03b5\u03c0\u03c4\u03c5\u03b3\u03bc\u03b5\u0301\u03bd\u03c9\u03bd \u03c7\u03c9\u03c1\u03c9\u0301\u03bd, \u03b1\u03ba\u03bf\u03bb\u03bf\u03c5\u03b8\u03bf\u03c5\u0301\u03bc\u03b5\u03bd\u03b7 \u03b1\u03c0\u03bf\u0301 \u03c4\u03b7\u03bd \u0395\u03bb\u03bb\u03b1\u0301\u03b4\u03b1 (174%), \u03c4\u03b7\u03bd \u0399\u03c4\u03b1\u03bb\u03b9\u0301\u03b1 (133,1%) \u03ba\u03b1\u03b9 \u03c4\u03b7\u03bd \u03a0\u03bf\u03c1\u03c4\u03bf\u03b3\u03b1\u03bb\u03b9\u0301\u03b1 (125,3%). \u039f\u03b9 \u0397\u03a0\u0391, \u03bf\u03b9 \u03bf\u03c0\u03bf\u03b9\u0301\u03b5\u03c2 \u03b5\u0301\u03c7\u03bf\u03c5\u03bd \u03c0\u03b1\u03c1\u03b1\u03bb\u03c5\u0301\u03c3\u03b5\u03b9 \u03b1\u03c0\u03bf\u0301 \u03b5\u0301\u03bd\u03b1 \u03b4\u03b7\u03bc\u03bf\u03c3\u03b9\u03bf\u03bd\u03bf\u03bc\u03b9\u03ba\u03bf\u0301 \u03b1\u03b4\u03b9\u03b5\u0301\u03be\u03bf\u03b4\u03bf \u03ba\u03b1\u03b9 \u03b1\u03c0\u03b5\u03b9\u03bb\u03bf\u03c5\u0301\u03bd\u03c4\u03b1\u03b9 \u03b1\u03c0\u03bf\u0301 \u03bc\u03b9\u03b1 \u03c0\u03b9\u03b8\u03b1\u03bd\u03b7\u0301 \u03c3\u03c4\u03b1\u0301\u03c3\u03b7 \u03c0\u03bb\u03b7\u03c1\u03c9\u03bc\u03c9\u0301\u03bd, \u03b8\u03b1 \u03b4\u03bf\u03c5\u03bd \u03c4\u03bf \u03c7\u03c1\u03b5\u0301\u03bf\u03c2 \u03c4\u03bf\u03c5\u03c2 \u03bd\u03b1 \u03b1\u03bd\u03b5\u03b2\u03b1\u03b9\u0301\u03bd\u03b5\u03b9 \u03c3\u03c4\u03bf 107,3% \u03c4\u03bf\u03c5 \u0391\u0395\u03a0 \u03c4\u03bf\u03c5\u03c2 \u03c4\u03bf 2014, \u03b4\u03b7\u03bb\u03b1\u03b4\u03b7\u0301 \u03b8\u03b1 \u03b2\u03c1\u03b9\u0301\u03c3\u03ba\u03bf\u03bd\u03c4\u03b1\u03b9 \u03c0\u03bf\u03bb\u03c5\u0301 \u03c0\u03b9\u03bf \u03bc\u03c0\u03c1\u03bf\u03c3\u03c4\u03b1\u0301 \u03b1\u03c0\u03bf\u0301 \u03c4\u03b7\u03bd \u0393\u03b1\u03bb\u03bb\u03b9\u0301\u03b1 \u03ba\u03b1\u03b9 \u03c4\u03bf 94,8% \u03c3\u03c4\u03bf \u03bf\u03c0\u03bf\u03b9\u0301\u03bf \u03b1\u03bd\u03b1\u03bc\u03b5\u0301\u03bd\u03b5\u03c4\u03b1\u03b9 \u03bf\u0301\u03c4\u03b9 \u03b8\u03b1 \u03b1\u03bd\u03b5\u0301\u03c1\u03c7\u03b5\u03c4\u03b1\u03b9 \u03c4\u03b7\u03bd \u03b5\u03c1\u03c7\u03bf\u0301\u03bc\u03b5\u03bd\u03b7 \u03c7\u03c1\u03bf\u03bd\u03b9\u03b1\u0301 \u03c4\u03bf \u03c7\u03c1\u03b5\u0301\u03bf\u03c2 \u03c4\u03b7\u03c2. \u0397 \u03b4\u03b5\u03c5\u0301\u03c4\u03b5\u03c1\u03b7 \u03bf\u03b9\u03ba\u03bf\u03bd\u03bf\u03bc\u03b9\u03ba\u03b7\u0301 \u03b4\u03c5\u0301\u03bd\u03b1\u03bc\u03b7 \u03c4\u03bf\u03c5 \u03ba\u03bf\u0301\u03c3\u03bc\u03bf\u03c5, \u03b7 \u039a\u03b9\u0301\u03bd\u03b1 \u03b4\u03b9\u0301\u03bd\u03b5\u03b9 \u03c4\u03b7\u03bd \u03b5\u03b9\u03ba\u03bf\u0301\u03bd\u03b1 \u03c4\u03bf\u03c5 \u03ba\u03b1\u03bb\u03bf\u03c5\u0301 \u03bc\u03b1\u03b8\u03b7\u03c4\u03b7\u0301 \u03bc\u03b5 \u03bc\u03b9\u03b1 \u03b1\u03bd\u03b1\u03bb\u03bf\u03b3\u03b9\u0301\u03b1 \u03c7\u03c1\u03b5\u0301\u03bf\u03c5\u03c2/\u0391\u0395\u03a0 \u03bc\u03bf\u0301\u03bd\u03bf\u03bd 20,9% \u03c4\u03b7\u03bd \u03b5\u03c1\u03c7\u03bf\u0301\u03bc\u03b5\u03bd\u03b7 \u03c7\u03c1\u03bf\u03bd\u03b9\u03b1\u0301, \u03c3\u03c5\u0301\u03bc\u03c6\u03c9\u03bd\u03b1 \u03bc\u03b5 \u03c4\u03bf \u0394\u039d\u03a4. \"\"\u03a0\u03b1\u03c1\u03b1\u0301 \u03c4\u03b9\u03c2 \u03c0\u03c1\u03bf\u03bf\u0301\u03b4\u03bf\u03c5\u03c2 \u03c3\u03c4\u03b7 \u03bc\u03b5\u03b9\u0301\u03c9\u03c3\u03b7 \u03c4\u03c9\u03bd \u03b5\u03bb\u03bb\u03b5\u03b9\u03bc\u03bc\u03b1\u0301\u03c4\u03c9\u03bd, \u03bf\u03b9 \u03b4\u03b7\u03bc\u03bf\u03c3\u03b9\u03bf\u03bd\u03bf\u03bc\u03b9\u03ba\u03b5\u0301\u03c2 \u03b1\u03b4\u03c5\u03bd\u03b1\u03bc\u03b9\u0301\u03b5\u03c2 \u03c0\u03b1\u03c1\u03b1\u03bc\u03b5\u0301\u03bd\u03bf\u03c5\u03bd \u03b2\u03b1\u03b8\u03b9\u03b5\u0301\u03c2 \u03c3\u03c4\u03b9\u03c2 \u03b1\u03bd\u03b5\u03c0\u03c4\u03c5\u03b3\u03bc\u03b5\u0301\u03bd\u03b5\u03c2 \u03c7\u03c9\u0301\u03c1\u03b5\u03c2\"\", \u03b5\u03c0\u03b9\u03c3\u03b7\u03bc\u03b1\u03b9\u0301\u03bd\u03b5\u03c4\u03b1\u03b9 \u03c3\u03c4\u03b7\u03bd \u03b5\u0301\u03ba\u03b8\u03b5\u03c3\u03b7. \u0391\u03c0\u03b5\u0301\u03bd\u03b1\u03bd\u03c4\u03b9 \u03c3\u03b5 \u03b1\u03c5\u03c4\u03b5\u0301\u03c2 \u03c4\u03b9\u03c2 \u03b1\u03bd\u03b9\u03c3\u03bf\u03c1\u03c1\u03bf\u03c0\u03b9\u0301\u03b5\u03c2, \u03c4\u03bf \u0394\u039d\u03a4 \u03b5\u03ba\u03c6\u03c1\u03b1\u0301\u03b6\u03b5\u03b9 \u03c4\u03b7\u03bd \u03b1\u03bd\u03b7\u03c3\u03c5\u03c7\u03b9\u0301\u03b1 \u03c4\u03bf\u03c5 \u03ba\u03b1\u03b8\u03c9\u0301\u03c2 \u03b2\u03bb\u03b5\u0301\u03c0\u03b5\u03b9 \"\"\u03b5\u0301\u03bd\u03b1 \u03c6\u03bf\u03c1\u03bf\u03bb\u03bf\u03b3\u03b9\u03ba\u03bf\u0301 \u03c3\u03c5\u0301\u03c3\u03c4\u03b7\u03bc\u03b1 \u03c5\u03c0\u03bf\u0301 \u03c0\u03b9\u0301\u03b5\u03c3\u03b7\"\", \u03c4\u03bf \u03bf\u03c0\u03bf\u03b9\u0301\u03bf \u03b5\u03c5\u03bd\u03bf\u03b5\u03b9\u0301 \u03c4\u03bf\u03bd \u03b1\u03bd\u03c4\u03b1\u03b3\u03c9\u03bd\u03b9\u03c3\u03bc\u03bf\u0301 \u03bc\u03b5\u03c4\u03b1\u03be\u03c5\u0301 \u03c4\u03c9\u03bd \u03ba\u03c1\u03b1\u03c4\u03c9\u0301\u03bd \u03ba\u03b1\u03b9 \u03b5\u03c0\u03b9\u03c4\u03c1\u03b5\u0301\u03c0\u03b5\u03b9 \u03c3\u03c4\u03bf\u03c5\u03c2 \u03b5\u03c5\u0301\u03c0\u03bf\u03c1\u03bf\u03c5\u03c2 \u03c6\u03bf\u03c1\u03bf\u03bb\u03bf\u03b3\u03bf\u03c5\u0301\u03bc\u03b5\u03bd\u03bf\u03c5\u03c2 \u03ba\u03b1\u03b9 \u03c3\u03c4\u03b9\u03c2 \u03c0\u03bf\u03bb\u03c5\u03b5\u03b8\u03bd\u03b9\u03ba\u03b5\u0301\u03c2 \u03bd\u03b1 \u03b5\u03bb\u03b1\u03c6\u03c1\u03c5\u0301\u03bd\u03bf\u03c5\u03bd \u03c4\u03bf\u03c5\u03c2 \u03c6\u03bf\u0301\u03c1\u03bf\u03c5\u03c2 \u03c4\u03bf\u03c5\u03c2. \u039c\u03bf\u0301\u03bd\u03bf\u03bd \u03c3\u03c4\u03b9\u03c2 \u0397\u03a0\u0391, \u03c4\u03bf \u0394\u039d\u03a4 \u03c5\u03c0\u03bf\u03bb\u03bf\u03b3\u03b9\u0301\u03b6\u03b5\u03b9 \u03c3\u03b5 60 \u03b4\u03b9\u03c3\u03b5\u03ba\u03b1\u03c4\u03bf\u03bc\u03bc\u03c5\u0301\u03c1\u03b9\u03b1 \u03b4\u03bf\u03bb\u03b1\u0301\u03c1\u03b9\u03b1 \u03c4\u03b1 \u03b5\u0301\u03c3\u03bf\u03b4\u03b1 \u03c0\u03bf\u03c5 \u03c6\u03b5\u0301\u03c1\u03b5\u03c4\u03b1\u03b9 \u03bf\u0301\u03c4\u03b9 \u03c7\u03b1\u0301\u03bd\u03bf\u03bd\u03c4\u03b1\u03b9 \u03bb\u03bf\u0301\u03b3\u03c9 \u03c4\u03b5\u03c7\u03bd\u03b9\u03ba\u03c9\u0301\u03bd \u03b2\u03b5\u03bb\u03c4\u03b9\u03c3\u03c4\u03bf\u03c0\u03bf\u03b9\u0301\u03b7\u03c3\u03b7\u03c2 \u03c4\u03b7\u03c2 \u03c6\u03bf\u03c1\u03bf\u03bb\u03bf\u03b3\u03b9\u0301\u03b1\u03c2 \u03c4\u03c9\u03bd \u03c0\u03bf\u03bb\u03c5\u03b5\u03b8\u03bd\u03b9\u03ba\u03c9\u0301\u03bd. \u03a4\u03bf \u0394\u039d\u03a4 \u03b5\u03c0\u03b9\u03c3\u03b7\u03bc\u03b1\u03b9\u0301\u03bd\u03b5\u03b9 \u03bf\u0301\u03c4\u03b9 \u03bf\u03b9 \u03c4\u03b5\u03bb\u03b5\u03c5\u03c4\u03b1\u03b9\u0301\u03b5\u03c2 \u03b4\u03b5\u03ba\u03b1\u03b5\u03c4\u03b9\u0301\u03b5\u03c2 \u03b5\u0301\u03c7\u03bf\u03c5\u03bd \u03c3\u03b7\u03bc\u03b1\u03c4\u03bf\u03b4\u03bf\u03c4\u03b7\u03b8\u03b5\u03b9\u0301 \u03b1\u03c0\u03bf\u0301 \u03bc\u03b9\u03b1 \"\"\u03b8\u03b5\u03b1\u03bc\u03b1\u03c4\u03b9\u03ba\u03b7\u0301 \u03b1\u0301\u03bd\u03bf\u03b4\u03bf\"\" \u03c4\u03bf\u03c5 \u03c0\u03bb\u03bf\u03c5\u0301\u03c4\u03bf\u03c5 \u03c4\u03bf\u03c5 \"\"1%\"\" \u03c4\u03c9\u03bd \u03c0\u03b9\u03bf \u03c0\u03bb\u03bf\u03c5\u0301\u03c3\u03b9\u03c9\u03bd, \u03ba\u03c5\u03c1\u03b9\u0301\u03c9\u03c2 \u03c3\u03c4\u03bf\u03bd \u03b1\u03b3\u03b3\u03bb\u03bf\u03c3\u03b1\u03be\u03bf\u03bd\u03b9\u03ba\u03bf\u0301 \u03ba\u03bf\u0301\u03c3\u03bc\u03bf, \u03c7\u03c9\u03c1\u03b9\u0301\u03c2 \u03c9\u03c3\u03c4\u03bf\u0301\u03c3\u03bf \u03b7 \u03c6\u03bf\u03c1\u03bf\u03bb\u03bf\u03b3\u03b9\u0301\u03b1 \u03bd\u03b1 \u03b5\u0301\u03c7\u03b5\u03b9 \u03c0\u03c1\u03bf\u03c3\u03b1\u03c1\u03bc\u03bf\u03c3\u03c4\u03b5\u03b9\u0301 \u03c3\u03b5 \u03b1\u03c5\u03c4\u03b7\u0301\u03bd \u03c4\u03b7\u03bd \u03b5\u03be\u03b5\u0301\u03bb\u03b9\u03be\u03b7. \"\"\u03a3\u03b5 \u03c0\u03bf\u03bb\u03bb\u03b5\u0301\u03c2 \u03c7\u03c9\u0301\u03c1\u03b5\u03c2 \u03b8\u03b1 \u03b7\u0301\u03c4\u03b1\u03bd \u03c0\u03b9\u03b8\u03b1\u03bd\u03bf\u0301 \u03bd\u03b1 \u03b5\u03c0\u03b9\u03b2\u03bb\u03b7\u03b8\u03bf\u03c5\u0301\u03bd \u03b5\u03c0\u03b9\u03c0\u03bb\u03b5\u0301\u03bf\u03bd \u03c6\u03bf\u0301\u03c1\u03bf\u03b9 \u03c3\u03b5 \u03b1\u03c5\u03c4\u03bf\u03c5\u0301\u03c2 \u03c0\u03bf\u03c5 \u03b4\u03b9\u03b1\u03b8\u03b5\u0301\u03c4\u03bf\u03c5\u03bd \u03c4\u03b1 \u03c0\u03b9\u03bf \u03c5\u03c8\u03b7\u03bb\u03b1\u0301 \u03b5\u03b9\u03c3\u03bf\u03b4\u03b7\u0301\u03bc\u03b1\u03c4\u03b1\"\", \u03c5\u03c0\u03bf\u03b3\u03c1\u03b1\u03bc\u03bc\u03b9\u0301\u03b6\u03b5\u03b9 \u03c4\u03bf \u0394\u039d\u03a4, \u03c4\u03bf \u03bf\u03c0\u03bf\u03b9\u0301\u03bf \u03ba\u03c1\u03b9\u0301\u03bd\u03b5\u03b9 \u03b5\u03be\u03b1\u0301\u03bb\u03bb\u03bf\u03c5 \"\"\u03c3\u03c5\u03bd\u03b5\u03c4\u03bf\u0301\"\" \u03c4\u03bf\u03bd \u03c5\u03c0\u03bf\u03bb\u03bf\u03b3\u03b9\u03c3\u03bc\u03bf\u0301 \u03c3\u03b5 4.500 \u03b4\u03b9\u03c3\u03b5\u03ba\u03b1\u03c4\u03bf\u03bc\u03bc\u03c5\u0301\u03c1\u03b9\u03b1 \u03b4\u03bf\u03bb\u03b1\u0301\u03c1\u03b9\u03b1 \u03c4\u03c9\u03bd \u03b4\u03b9\u03b1\u03b8\u03b5\u03c3\u03b9\u0301\u03bc\u03c9\u03bd \u03c0\u03bf\u03c5 \u03b1\u03c0\u03bf\u03ba\u03c1\u03c5\u0301\u03c0\u03c4\u03bf\u03bd\u03c4\u03b1\u03b9 \u03b1\u03c0\u03bf\u0301 \u03b9\u03b4\u03b9\u03c9\u0301\u03c4\u03b5\u03c2 \u03c3\u03b5 \u03c6\u03bf\u03c1\u03bf\u03bb\u03bf\u03b3\u03b9\u03ba\u03bf\u03c5\u0301\u03c2 \u03c0\u03b1\u03c1\u03b1\u03b4\u03b5\u03b9\u0301\u03c3\u03bf\u03c5\u03c2. \u039f\u03b9 \u03c7\u03c9\u0301\u03c1\u03b5\u03c2 \u03c4\u03b7\u03c2 \u039f\u03bc\u03b1\u0301\u03b4\u03b1\u03c2 \u03c4\u03c9\u03bd \u0395\u03b9\u0301\u03ba\u03bf\u03c3\u03b9 (G20), \u03bf\u03b9 \u03c5\u03c0\u03bf\u03c5\u03c1\u03b3\u03bf\u03b9\u0301 \u039f\u03b9\u03ba\u03bf\u03bd\u03bf\u03bc\u03b9\u03ba\u03c9\u0301\u03bd \u03c4\u03c9\u03bd \u03bf\u03c0\u03bf\u03b9\u0301\u03c9\u03bd \u03c3\u03c5\u03bd\u03b1\u03bd\u03c4\u03c9\u0301\u03bd\u03c4\u03b1\u03b9 \u03b1\u03c5\u03c4\u03b7\u0301\u03bd \u03c4\u03b7\u03bd \u03b5\u03b2\u03b4\u03bf\u03bc\u03b1\u0301\u03b4\u03b1 \u03c3\u03c4\u03b7\u03bd \u039f\u03c5\u03b1\u0301\u03c3\u03b9\u03bd\u03b3\u03ba\u03c4\u03bf\u03bd, \u03be\u03b5\u03ba\u03b9\u0301\u03bd\u03b7\u03c3\u03b1\u03bd \u03c0\u03c1\u03bf\u0301\u03c3\u03c6\u03b1\u03c4\u03b1 \u03c0\u03c1\u03c9\u03c4\u03bf\u03b2\u03bf\u03c5\u03bb\u03b9\u0301\u03b5\u03c2 \u03b3\u03b9\u03b1 \u03c4\u03b7\u03bd \u03c0\u03b1\u0301\u03c4\u03b1\u03be\u03b7 \u03c4\u03b7\u03c2 \u03c6\u03bf\u03c1\u03bf\u03b4\u03b9\u03b1\u03c6\u03c5\u03b3\u03b7\u0301\u03c2.", "example_title": "Economics"}], "model-index": [{"name": "IMISLab/GreekT5-umt5-small-greeksum", "results": [{"task": {"type": "summarization", "name": "Summarization"}, "dataset": {"name": "GreekSUM", "type": "greeksum", "config": "default", "split": "test"}, "metrics": [{"type": "rouge", "value": 25.49, "name": "ROUGE-1", "verified": true}, {"type": "rouge", "value": 12.03, "name": "ROUGE-2", "verified": true}, {"type": "rouge", "value": 21.32, "name": "ROUGE-L", "verified": true}, {"type": "bertscore", "value": 72.86, "name": "BERTScore", "verified": true}]}]}]}

summarization

IMISLab/GreekT5-umt5-small-greeksum

2023-11-12T10:06:04+00:00

TAGS #transformers #pytorch #umt5 #text2text-generation #summarization #el #arxiv-2311.07767 #arxiv-2304.00869 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us

GreekT5 (umt5-small-greeksum) ============================= A Greek news summarization model trained on GreekSum. This model is part of a series of models trained as part of our research paper: Giarelis, N., Mastrokostas, C., & Karacapilidis, N. (2023). GreekT5: A Series of Greek Sequence-to-Sequence Models for News Summarization. The proposed models were trained and evaluated on the same dataset against GreekBART. For more information see the evaluation section below. ![]() Training dataset ---------------- The training dataset of 'GreekT5-umt5-small-greeksum' is GreekSum, which is the first news summarization dataset for the Greek Language. This dataset contains ~151,000 news articles collected from News24/7, belonging to various topics (i.e., society, politics, economy, culture or world news). For more information see: URL Training configuration ---------------------- We trained 'google/umt5-small' [300 million parameters (~1.20 GB)] on the GreekSUM train split using the following parameters: * GPU batch size = 6 * Total training epochs = 10 * AdamW optimizer (e = 1e−8, β1 = 0.9 and β2 = 0.0999) * Learning rate = 3e−4 * Linear weight decay * No warmup steps * 32-bit floating precision * Tokenization + maximum input token length = 1024 + maximum output token length = 128 + padding = ‘max\_length’ + truncation = True Note: T5-based models use a multi-task architecture, the prefix *‘summarize: ’* was prepended in each training sample. Evaluation ---------- ### Example code Contact ------- If you have any questions/feedback about the model please e-mail one of the following authors: The model has been officially released with the article: GreekT5: A Series of Greek Sequence-to-Sequence Models for News Summarization. If you use the model, please cite the following:

# Lora of airi_akizuki_onichichi This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). And the auto-training framework is maintained by [DeepGHS Team](https://huggingface.co/deepghs). The base model used during training is [NAI](https://huggingface.co/deepghs/animefull-latest), and the base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11). After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora. For example, if you want to use the model from step 21900, you need to download `21900/airi_akizuki_onichichi.pt` as the embedding and `21900/airi_akizuki_onichichi.safetensors` for loading Lora. By using both files together, you can generate images for the desired characters. **The best step we recommend is 21900**, with the score of 0.888. The trigger words are: 1. `airi_akizuki_onichichi` 2. `blonde_hair, blush, twintails, blue_eyes, long_hair, breasts` For the following groups, it is not recommended to use this model and we express regret: 1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail. 2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits. 3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm. 4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters. 5. Individuals who finds the generated image content offensive to their values. These are available steps: | Steps | Score | Download | pattern_1 | pattern_2 | pattern_3 | pattern_4 | pattern_5 | pattern_6 | pattern_7 | pattern_8 | pattern_9 | pattern_10 | pattern_11 | pattern_12 | pattern_13 | pattern_14 | pattern_15 | pattern_16 | pattern_17 | pattern_18 | pattern_19 | pattern_20 | pattern_21 | pattern_22 | pattern_23 | pattern_24 | pattern_25 | pattern_26 | pattern_27 | pattern_28 | pattern_29 | pattern_30 | pattern_31 | pattern_32 | pattern_33 | pattern_34 | pattern_35 | pattern_36 | pattern_37 | pattern_38 | pattern_39 | pattern_40 | pattern_41 | pattern_42 | pattern_43 | bikini | bondage | free | maid | miko | nude | nude2 | suit | yukata | |:----------|:----------|:-------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:-------------------------------------------------|:---------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:---------------------------------------------------|:------------------------------------------------------|:---------------------------------------------------|:---------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:---------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:---------------------------------------------------|:---------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:---------------------------------------------------|:---------------------------------------------------|:---------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:------------------------------------------------------|:-------------------------------------------|:---------------------------------------------------|:------------------------------------------------|:---------------------------------------|:---------------------------------------|:------------------------------------------------|:-------------------------------------------------|:---------------------------------------|:-------------------------------------------| | **21900** | **0.888** | [**Download**](21900/airi_akizuki_onichichi.zip) |  | [<NSFW, click to see>](21900/previews/pattern_2.png) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](21900/previews/pattern_11.png) | [<NSFW, click to see>](21900/previews/pattern_12.png) | [<NSFW, click to see>](21900/previews/pattern_13.png) |  | [<NSFW, click to see>](21900/previews/pattern_15.png) |  |  | [<NSFW, click to see>](21900/previews/pattern_18.png) | [<NSFW, click to see>](21900/previews/pattern_19.png) | [<NSFW, click to see>](21900/previews/pattern_20.png) | [<NSFW, click to see>](21900/previews/pattern_21.png) | [<NSFW, click to see>](21900/previews/pattern_22.png) | [<NSFW, click to see>](21900/previews/pattern_23.png) | [<NSFW, click to see>](21900/previews/pattern_24.png) | [<NSFW, click to see>](21900/previews/pattern_25.png) | [<NSFW, click to see>](21900/previews/pattern_26.png) | [<NSFW, click to see>](21900/previews/pattern_27.png) | [<NSFW, click to see>](21900/previews/pattern_28.png) |  | [<NSFW, click to see>](21900/previews/pattern_30.png) | [<NSFW, click to see>](21900/previews/pattern_31.png) |  |  | [<NSFW, click to see>](21900/previews/pattern_34.png) | [<NSFW, click to see>](21900/previews/pattern_35.png) | [<NSFW, click to see>](21900/previews/pattern_36.png) | [<NSFW, click to see>](21900/previews/pattern_37.png) |  |  |  | [<NSFW, click to see>](21900/previews/pattern_41.png) | [<NSFW, click to see>](21900/previews/pattern_42.png) | [<NSFW, click to see>](21900/previews/pattern_43.png) |  | [<NSFW, click to see>](21900/previews/bondage.png) | [<NSFW, click to see>](21900/previews/free.png) |  |  | [<NSFW, click to see>](21900/previews/nude.png) | [<NSFW, click to see>](21900/previews/nude2.png) |  |  | | 20440 | 0.852 | [Download](20440/airi_akizuki_onichichi.zip) |  | [<NSFW, click to see>](20440/previews/pattern_2.png) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](20440/previews/pattern_11.png) | [<NSFW, click to see>](20440/previews/pattern_12.png) | [<NSFW, click to see>](20440/previews/pattern_13.png) |  | [<NSFW, click to see>](20440/previews/pattern_15.png) |  |  | [<NSFW, click to see>](20440/previews/pattern_18.png) | [<NSFW, click to see>](20440/previews/pattern_19.png) | [<NSFW, click to see>](20440/previews/pattern_20.png) | [<NSFW, click to see>](20440/previews/pattern_21.png) | [<NSFW, click to see>](20440/previews/pattern_22.png) | [<NSFW, click to see>](20440/previews/pattern_23.png) | [<NSFW, click to see>](20440/previews/pattern_24.png) | [<NSFW, click to see>](20440/previews/pattern_25.png) | [<NSFW, click to see>](20440/previews/pattern_26.png) | [<NSFW, click to see>](20440/previews/pattern_27.png) | [<NSFW, click to see>](20440/previews/pattern_28.png) |  | [<NSFW, click to see>](20440/previews/pattern_30.png) | [<NSFW, click to see>](20440/previews/pattern_31.png) |  |  | [<NSFW, click to see>](20440/previews/pattern_34.png) | [<NSFW, click to see>](20440/previews/pattern_35.png) | [<NSFW, click to see>](20440/previews/pattern_36.png) | [<NSFW, click to see>](20440/previews/pattern_37.png) |  |  |  | [<NSFW, click to see>](20440/previews/pattern_41.png) | [<NSFW, click to see>](20440/previews/pattern_42.png) | [<NSFW, click to see>](20440/previews/pattern_43.png) |  | [<NSFW, click to see>](20440/previews/bondage.png) | [<NSFW, click to see>](20440/previews/free.png) |  |  | [<NSFW, click to see>](20440/previews/nude.png) | [<NSFW, click to see>](20440/previews/nude2.png) |  |  | | 18980 | 0.877 | [Download](18980/airi_akizuki_onichichi.zip) |  | [<NSFW, click to see>](18980/previews/pattern_2.png) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](18980/previews/pattern_11.png) | [<NSFW, click to see>](18980/previews/pattern_12.png) | [<NSFW, click to see>](18980/previews/pattern_13.png) |  | [<NSFW, click to see>](18980/previews/pattern_15.png) |  |  | [<NSFW, click to see>](18980/previews/pattern_18.png) | [<NSFW, click to see>](18980/previews/pattern_19.png) | [<NSFW, click to see>](18980/previews/pattern_20.png) | [<NSFW, click to see>](18980/previews/pattern_21.png) | [<NSFW, click to see>](18980/previews/pattern_22.png) | [<NSFW, click to see>](18980/previews/pattern_23.png) | [<NSFW, click to see>](18980/previews/pattern_24.png) | [<NSFW, click to see>](18980/previews/pattern_25.png) | [<NSFW, click to see>](18980/previews/pattern_26.png) | [<NSFW, click to see>](18980/previews/pattern_27.png) | [<NSFW, click to see>](18980/previews/pattern_28.png) |  | [<NSFW, click to see>](18980/previews/pattern_30.png) | [<NSFW, click to see>](18980/previews/pattern_31.png) |  |  | [<NSFW, click to see>](18980/previews/pattern_34.png) | [<NSFW, click to see>](18980/previews/pattern_35.png) | [<NSFW, click to see>](18980/previews/pattern_36.png) | [<NSFW, click to see>](18980/previews/pattern_37.png) |  |  |  | [<NSFW, click to see>](18980/previews/pattern_41.png) | [<NSFW, click to see>](18980/previews/pattern_42.png) | [<NSFW, click to see>](18980/previews/pattern_43.png) |  | [<NSFW, click to see>](18980/previews/bondage.png) | [<NSFW, click to see>](18980/previews/free.png) |  |  | [<NSFW, click to see>](18980/previews/nude.png) | [<NSFW, click to see>](18980/previews/nude2.png) |  |  | | 17520 | 0.877 | [Download](17520/airi_akizuki_onichichi.zip) |  | [<NSFW, click to see>](17520/previews/pattern_2.png) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](17520/previews/pattern_11.png) | [<NSFW, click to see>](17520/previews/pattern_12.png) | [<NSFW, click to see>](17520/previews/pattern_13.png) |  | [<NSFW, click to see>](17520/previews/pattern_15.png) |  |  | [<NSFW, click to see>](17520/previews/pattern_18.png) | [<NSFW, click to see>](17520/previews/pattern_19.png) | [<NSFW, click to see>](17520/previews/pattern_20.png) | [<NSFW, click to see>](17520/previews/pattern_21.png) | [<NSFW, click to see>](17520/previews/pattern_22.png) | [<NSFW, click to see>](17520/previews/pattern_23.png) | [<NSFW, click to see>](17520/previews/pattern_24.png) | [<NSFW, click to see>](17520/previews/pattern_25.png) | [<NSFW, click to see>](17520/previews/pattern_26.png) | [<NSFW, click to see>](17520/previews/pattern_27.png) | [<NSFW, click to see>](17520/previews/pattern_28.png) |  | [<NSFW, click to see>](17520/previews/pattern_30.png) | [<NSFW, click to see>](17520/previews/pattern_31.png) |  |  | [<NSFW, click to see>](17520/previews/pattern_34.png) | [<NSFW, click to see>](17520/previews/pattern_35.png) | [<NSFW, click to see>](17520/previews/pattern_36.png) | [<NSFW, click to see>](17520/previews/pattern_37.png) |  |  |  | [<NSFW, click to see>](17520/previews/pattern_41.png) | [<NSFW, click to see>](17520/previews/pattern_42.png) | [<NSFW, click to see>](17520/previews/pattern_43.png) |  | [<NSFW, click to see>](17520/previews/bondage.png) | [<NSFW, click to see>](17520/previews/free.png) |  |  | [<NSFW, click to see>](17520/previews/nude.png) | [<NSFW, click to see>](17520/previews/nude2.png) |  |  | | 16060 | 0.875 | [Download](16060/airi_akizuki_onichichi.zip) |  | [<NSFW, click to see>](16060/previews/pattern_2.png) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](16060/previews/pattern_11.png) | [<NSFW, click to see>](16060/previews/pattern_12.png) | [<NSFW, click to see>](16060/previews/pattern_13.png) |  | [<NSFW, click to see>](16060/previews/pattern_15.png) |  |  | [<NSFW, click to see>](16060/previews/pattern_18.png) | [<NSFW, click to see>](16060/previews/pattern_19.png) | [<NSFW, click to see>](16060/previews/pattern_20.png) | [<NSFW, click to see>](16060/previews/pattern_21.png) | [<NSFW, click to see>](16060/previews/pattern_22.png) | [<NSFW, click to see>](16060/previews/pattern_23.png) | [<NSFW, click to see>](16060/previews/pattern_24.png) | [<NSFW, click to see>](16060/previews/pattern_25.png) | [<NSFW, click to see>](16060/previews/pattern_26.png) | [<NSFW, click to see>](16060/previews/pattern_27.png) | [<NSFW, click to see>](16060/previews/pattern_28.png) |  | [<NSFW, click to see>](16060/previews/pattern_30.png) | [<NSFW, click to see>](16060/previews/pattern_31.png) |  |  | [<NSFW, click to see>](16060/previews/pattern_34.png) | [<NSFW, click to see>](16060/previews/pattern_35.png) | [<NSFW, click to see>](16060/previews/pattern_36.png) | [<NSFW, click to see>](16060/previews/pattern_37.png) |  |  |  | [<NSFW, click to see>](16060/previews/pattern_41.png) | [<NSFW, click to see>](16060/previews/pattern_42.png) | [<NSFW, click to see>](16060/previews/pattern_43.png) |  | [<NSFW, click to see>](16060/previews/bondage.png) | [<NSFW, click to see>](16060/previews/free.png) |  |  | [<NSFW, click to see>](16060/previews/nude.png) | [<NSFW, click to see>](16060/previews/nude2.png) |  |  | | 14600 | 0.876 | [Download](14600/airi_akizuki_onichichi.zip) |  | [<NSFW, click to see>](14600/previews/pattern_2.png) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](14600/previews/pattern_11.png) | [<NSFW, click to see>](14600/previews/pattern_12.png) | [<NSFW, click to see>](14600/previews/pattern_13.png) |  | [<NSFW, click to see>](14600/previews/pattern_15.png) |  |  | [<NSFW, click to see>](14600/previews/pattern_18.png) | [<NSFW, click to see>](14600/previews/pattern_19.png) | [<NSFW, click to see>](14600/previews/pattern_20.png) | [<NSFW, click to see>](14600/previews/pattern_21.png) | [<NSFW, click to see>](14600/previews/pattern_22.png) | [<NSFW, click to see>](14600/previews/pattern_23.png) | [<NSFW, click to see>](14600/previews/pattern_24.png) | [<NSFW, click to see>](14600/previews/pattern_25.png) | [<NSFW, click to see>](14600/previews/pattern_26.png) | [<NSFW, click to see>](14600/previews/pattern_27.png) | [<NSFW, click to see>](14600/previews/pattern_28.png) |  | [<NSFW, click to see>](14600/previews/pattern_30.png) | [<NSFW, click to see>](14600/previews/pattern_31.png) |  |  | [<NSFW, click to see>](14600/previews/pattern_34.png) | [<NSFW, click to see>](14600/previews/pattern_35.png) | [<NSFW, click to see>](14600/previews/pattern_36.png) | [<NSFW, click to see>](14600/previews/pattern_37.png) |  |  |  | [<NSFW, click to see>](14600/previews/pattern_41.png) | [<NSFW, click to see>](14600/previews/pattern_42.png) | [<NSFW, click to see>](14600/previews/pattern_43.png) |  | [<NSFW, click to see>](14600/previews/bondage.png) | [<NSFW, click to see>](14600/previews/free.png) |  |  | [<NSFW, click to see>](14600/previews/nude.png) | [<NSFW, click to see>](14600/previews/nude2.png) |  |  | | 13140 | 0.859 | [Download](13140/airi_akizuki_onichichi.zip) |  | [<NSFW, click to see>](13140/previews/pattern_2.png) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](13140/previews/pattern_11.png) | [<NSFW, click to see>](13140/previews/pattern_12.png) | [<NSFW, click to see>](13140/previews/pattern_13.png) |  | [<NSFW, click to see>](13140/previews/pattern_15.png) |  |  | [<NSFW, click to see>](13140/previews/pattern_18.png) | [<NSFW, click to see>](13140/previews/pattern_19.png) | [<NSFW, click to see>](13140/previews/pattern_20.png) | [<NSFW, click to see>](13140/previews/pattern_21.png) | [<NSFW, click to see>](13140/previews/pattern_22.png) | [<NSFW, click to see>](13140/previews/pattern_23.png) | [<NSFW, click to see>](13140/previews/pattern_24.png) | [<NSFW, click to see>](13140/previews/pattern_25.png) | [<NSFW, click to see>](13140/previews/pattern_26.png) | [<NSFW, click to see>](13140/previews/pattern_27.png) | [<NSFW, click to see>](13140/previews/pattern_28.png) |  | [<NSFW, click to see>](13140/previews/pattern_30.png) | [<NSFW, click to see>](13140/previews/pattern_31.png) |  |  | [<NSFW, click to see>](13140/previews/pattern_34.png) | [<NSFW, click to see>](13140/previews/pattern_35.png) | [<NSFW, click to see>](13140/previews/pattern_36.png) | [<NSFW, click to see>](13140/previews/pattern_37.png) |  |  |  | [<NSFW, click to see>](13140/previews/pattern_41.png) | [<NSFW, click to see>](13140/previews/pattern_42.png) | [<NSFW, click to see>](13140/previews/pattern_43.png) |  | [<NSFW, click to see>](13140/previews/bondage.png) | [<NSFW, click to see>](13140/previews/free.png) |  |  | [<NSFW, click to see>](13140/previews/nude.png) | [<NSFW, click to see>](13140/previews/nude2.png) |  |  | | 11680 | 0.865 | [Download](11680/airi_akizuki_onichichi.zip) |  | [<NSFW, click to see>](11680/previews/pattern_2.png) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](11680/previews/pattern_11.png) | [<NSFW, click to see>](11680/previews/pattern_12.png) | [<NSFW, click to see>](11680/previews/pattern_13.png) |  | [<NSFW, click to see>](11680/previews/pattern_15.png) |  |  | [<NSFW, click to see>](11680/previews/pattern_18.png) | [<NSFW, click to see>](11680/previews/pattern_19.png) | [<NSFW, click to see>](11680/previews/pattern_20.png) | [<NSFW, click to see>](11680/previews/pattern_21.png) | [<NSFW, click to see>](11680/previews/pattern_22.png) | [<NSFW, click to see>](11680/previews/pattern_23.png) | [<NSFW, click to see>](11680/previews/pattern_24.png) | [<NSFW, click to see>](11680/previews/pattern_25.png) | [<NSFW, click to see>](11680/previews/pattern_26.png) | [<NSFW, click to see>](11680/previews/pattern_27.png) | [<NSFW, click to see>](11680/previews/pattern_28.png) |  | [<NSFW, click to see>](11680/previews/pattern_30.png) | [<NSFW, click to see>](11680/previews/pattern_31.png) |  |  | [<NSFW, click to see>](11680/previews/pattern_34.png) | [<NSFW, click to see>](11680/previews/pattern_35.png) | [<NSFW, click to see>](11680/previews/pattern_36.png) | [<NSFW, click to see>](11680/previews/pattern_37.png) |  |  |  | [<NSFW, click to see>](11680/previews/pattern_41.png) | [<NSFW, click to see>](11680/previews/pattern_42.png) | [<NSFW, click to see>](11680/previews/pattern_43.png) |  | [<NSFW, click to see>](11680/previews/bondage.png) | [<NSFW, click to see>](11680/previews/free.png) |  |  | [<NSFW, click to see>](11680/previews/nude.png) | [<NSFW, click to see>](11680/previews/nude2.png) |  |  | | 10220 | 0.856 | [Download](10220/airi_akizuki_onichichi.zip) |  | [<NSFW, click to see>](10220/previews/pattern_2.png) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](10220/previews/pattern_11.png) | [<NSFW, click to see>](10220/previews/pattern_12.png) | [<NSFW, click to see>](10220/previews/pattern_13.png) |  | [<NSFW, click to see>](10220/previews/pattern_15.png) |  |  | [<NSFW, click to see>](10220/previews/pattern_18.png) | [<NSFW, click to see>](10220/previews/pattern_19.png) | [<NSFW, click to see>](10220/previews/pattern_20.png) | [<NSFW, click to see>](10220/previews/pattern_21.png) | [<NSFW, click to see>](10220/previews/pattern_22.png) | [<NSFW, click to see>](10220/previews/pattern_23.png) | [<NSFW, click to see>](10220/previews/pattern_24.png) | [<NSFW, click to see>](10220/previews/pattern_25.png) | [<NSFW, click to see>](10220/previews/pattern_26.png) | [<NSFW, click to see>](10220/previews/pattern_27.png) | [<NSFW, click to see>](10220/previews/pattern_28.png) |  | [<NSFW, click to see>](10220/previews/pattern_30.png) | [<NSFW, click to see>](10220/previews/pattern_31.png) |  |  | [<NSFW, click to see>](10220/previews/pattern_34.png) | [<NSFW, click to see>](10220/previews/pattern_35.png) | [<NSFW, click to see>](10220/previews/pattern_36.png) | [<NSFW, click to see>](10220/previews/pattern_37.png) |  |  |  | [<NSFW, click to see>](10220/previews/pattern_41.png) | [<NSFW, click to see>](10220/previews/pattern_42.png) | [<NSFW, click to see>](10220/previews/pattern_43.png) |  | [<NSFW, click to see>](10220/previews/bondage.png) | [<NSFW, click to see>](10220/previews/free.png) |  |  | [<NSFW, click to see>](10220/previews/nude.png) | [<NSFW, click to see>](10220/previews/nude2.png) |  |  | | 8760 | 0.861 | [Download](8760/airi_akizuki_onichichi.zip) |  | [<NSFW, click to see>](8760/previews/pattern_2.png) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](8760/previews/pattern_11.png) | [<NSFW, click to see>](8760/previews/pattern_12.png) | [<NSFW, click to see>](8760/previews/pattern_13.png) |  | [<NSFW, click to see>](8760/previews/pattern_15.png) |  |  | [<NSFW, click to see>](8760/previews/pattern_18.png) | [<NSFW, click to see>](8760/previews/pattern_19.png) | [<NSFW, click to see>](8760/previews/pattern_20.png) | [<NSFW, click to see>](8760/previews/pattern_21.png) | [<NSFW, click to see>](8760/previews/pattern_22.png) | [<NSFW, click to see>](8760/previews/pattern_23.png) | [<NSFW, click to see>](8760/previews/pattern_24.png) | [<NSFW, click to see>](8760/previews/pattern_25.png) | [<NSFW, click to see>](8760/previews/pattern_26.png) | [<NSFW, click to see>](8760/previews/pattern_27.png) | [<NSFW, click to see>](8760/previews/pattern_28.png) |  | [<NSFW, click to see>](8760/previews/pattern_30.png) | [<NSFW, click to see>](8760/previews/pattern_31.png) |  |  | [<NSFW, click to see>](8760/previews/pattern_34.png) | [<NSFW, click to see>](8760/previews/pattern_35.png) | [<NSFW, click to see>](8760/previews/pattern_36.png) | [<NSFW, click to see>](8760/previews/pattern_37.png) |  |  |  | [<NSFW, click to see>](8760/previews/pattern_41.png) | [<NSFW, click to see>](8760/previews/pattern_42.png) | [<NSFW, click to see>](8760/previews/pattern_43.png) |  | [<NSFW, click to see>](8760/previews/bondage.png) | [<NSFW, click to see>](8760/previews/free.png) |  |  | [<NSFW, click to see>](8760/previews/nude.png) | [<NSFW, click to see>](8760/previews/nude2.png) |  |  | | 7300 | 0.851 | [Download](7300/airi_akizuki_onichichi.zip) |  | [<NSFW, click to see>](7300/previews/pattern_2.png) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](7300/previews/pattern_11.png) | [<NSFW, click to see>](7300/previews/pattern_12.png) | [<NSFW, click to see>](7300/previews/pattern_13.png) |  | [<NSFW, click to see>](7300/previews/pattern_15.png) |  |  | [<NSFW, click to see>](7300/previews/pattern_18.png) | [<NSFW, click to see>](7300/previews/pattern_19.png) | [<NSFW, click to see>](7300/previews/pattern_20.png) | [<NSFW, click to see>](7300/previews/pattern_21.png) | [<NSFW, click to see>](7300/previews/pattern_22.png) | [<NSFW, click to see>](7300/previews/pattern_23.png) | [<NSFW, click to see>](7300/previews/pattern_24.png) | [<NSFW, click to see>](7300/previews/pattern_25.png) | [<NSFW, click to see>](7300/previews/pattern_26.png) | [<NSFW, click to see>](7300/previews/pattern_27.png) | [<NSFW, click to see>](7300/previews/pattern_28.png) |  | [<NSFW, click to see>](7300/previews/pattern_30.png) | [<NSFW, click to see>](7300/previews/pattern_31.png) |  |  | [<NSFW, click to see>](7300/previews/pattern_34.png) | [<NSFW, click to see>](7300/previews/pattern_35.png) | [<NSFW, click to see>](7300/previews/pattern_36.png) | [<NSFW, click to see>](7300/previews/pattern_37.png) |  |  |  | [<NSFW, click to see>](7300/previews/pattern_41.png) | [<NSFW, click to see>](7300/previews/pattern_42.png) | [<NSFW, click to see>](7300/previews/pattern_43.png) |  | [<NSFW, click to see>](7300/previews/bondage.png) | [<NSFW, click to see>](7300/previews/free.png) |  |  | [<NSFW, click to see>](7300/previews/nude.png) | [<NSFW, click to see>](7300/previews/nude2.png) |  |  | | 5840 | 0.835 | [Download](5840/airi_akizuki_onichichi.zip) |  | [<NSFW, click to see>](5840/previews/pattern_2.png) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](5840/previews/pattern_11.png) | [<NSFW, click to see>](5840/previews/pattern_12.png) | [<NSFW, click to see>](5840/previews/pattern_13.png) |  | [<NSFW, click to see>](5840/previews/pattern_15.png) |  |  | [<NSFW, click to see>](5840/previews/pattern_18.png) | [<NSFW, click to see>](5840/previews/pattern_19.png) | [<NSFW, click to see>](5840/previews/pattern_20.png) | [<NSFW, click to see>](5840/previews/pattern_21.png) | [<NSFW, click to see>](5840/previews/pattern_22.png) | [<NSFW, click to see>](5840/previews/pattern_23.png) | [<NSFW, click to see>](5840/previews/pattern_24.png) | [<NSFW, click to see>](5840/previews/pattern_25.png) | [<NSFW, click to see>](5840/previews/pattern_26.png) | [<NSFW, click to see>](5840/previews/pattern_27.png) | [<NSFW, click to see>](5840/previews/pattern_28.png) |  | [<NSFW, click to see>](5840/previews/pattern_30.png) | [<NSFW, click to see>](5840/previews/pattern_31.png) |  |  | [<NSFW, click to see>](5840/previews/pattern_34.png) | [<NSFW, click to see>](5840/previews/pattern_35.png) | [<NSFW, click to see>](5840/previews/pattern_36.png) | [<NSFW, click to see>](5840/previews/pattern_37.png) |  |  |  | [<NSFW, click to see>](5840/previews/pattern_41.png) | [<NSFW, click to see>](5840/previews/pattern_42.png) | [<NSFW, click to see>](5840/previews/pattern_43.png) |  | [<NSFW, click to see>](5840/previews/bondage.png) | [<NSFW, click to see>](5840/previews/free.png) |  |  | [<NSFW, click to see>](5840/previews/nude.png) | [<NSFW, click to see>](5840/previews/nude2.png) |  |  | | 4380 | 0.808 | [Download](4380/airi_akizuki_onichichi.zip) |  | [<NSFW, click to see>](4380/previews/pattern_2.png) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](4380/previews/pattern_11.png) | [<NSFW, click to see>](4380/previews/pattern_12.png) | [<NSFW, click to see>](4380/previews/pattern_13.png) |  | [<NSFW, click to see>](4380/previews/pattern_15.png) |  |  | [<NSFW, click to see>](4380/previews/pattern_18.png) | [<NSFW, click to see>](4380/previews/pattern_19.png) | [<NSFW, click to see>](4380/previews/pattern_20.png) | [<NSFW, click to see>](4380/previews/pattern_21.png) | [<NSFW, click to see>](4380/previews/pattern_22.png) | [<NSFW, click to see>](4380/previews/pattern_23.png) | [<NSFW, click to see>](4380/previews/pattern_24.png) | [<NSFW, click to see>](4380/previews/pattern_25.png) | [<NSFW, click to see>](4380/previews/pattern_26.png) | [<NSFW, click to see>](4380/previews/pattern_27.png) | [<NSFW, click to see>](4380/previews/pattern_28.png) |  | [<NSFW, click to see>](4380/previews/pattern_30.png) | [<NSFW, click to see>](4380/previews/pattern_31.png) |  |  | [<NSFW, click to see>](4380/previews/pattern_34.png) | [<NSFW, click to see>](4380/previews/pattern_35.png) | [<NSFW, click to see>](4380/previews/pattern_36.png) | [<NSFW, click to see>](4380/previews/pattern_37.png) |  |  |  | [<NSFW, click to see>](4380/previews/pattern_41.png) | [<NSFW, click to see>](4380/previews/pattern_42.png) | [<NSFW, click to see>](4380/previews/pattern_43.png) |  | [<NSFW, click to see>](4380/previews/bondage.png) | [<NSFW, click to see>](4380/previews/free.png) |  |  | [<NSFW, click to see>](4380/previews/nude.png) | [<NSFW, click to see>](4380/previews/nude2.png) |  |  | | 2920 | 0.772 | [Download](2920/airi_akizuki_onichichi.zip) |  | [<NSFW, click to see>](2920/previews/pattern_2.png) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](2920/previews/pattern_11.png) | [<NSFW, click to see>](2920/previews/pattern_12.png) | [<NSFW, click to see>](2920/previews/pattern_13.png) |  | [<NSFW, click to see>](2920/previews/pattern_15.png) |  |  | [<NSFW, click to see>](2920/previews/pattern_18.png) | [<NSFW, click to see>](2920/previews/pattern_19.png) | [<NSFW, click to see>](2920/previews/pattern_20.png) | [<NSFW, click to see>](2920/previews/pattern_21.png) | [<NSFW, click to see>](2920/previews/pattern_22.png) | [<NSFW, click to see>](2920/previews/pattern_23.png) | [<NSFW, click to see>](2920/previews/pattern_24.png) | [<NSFW, click to see>](2920/previews/pattern_25.png) | [<NSFW, click to see>](2920/previews/pattern_26.png) | [<NSFW, click to see>](2920/previews/pattern_27.png) | [<NSFW, click to see>](2920/previews/pattern_28.png) |  | [<NSFW, click to see>](2920/previews/pattern_30.png) | [<NSFW, click to see>](2920/previews/pattern_31.png) |  |  | [<NSFW, click to see>](2920/previews/pattern_34.png) | [<NSFW, click to see>](2920/previews/pattern_35.png) | [<NSFW, click to see>](2920/previews/pattern_36.png) | [<NSFW, click to see>](2920/previews/pattern_37.png) |  |  |  | [<NSFW, click to see>](2920/previews/pattern_41.png) | [<NSFW, click to see>](2920/previews/pattern_42.png) | [<NSFW, click to see>](2920/previews/pattern_43.png) |  | [<NSFW, click to see>](2920/previews/bondage.png) | [<NSFW, click to see>](2920/previews/free.png) |  |  | [<NSFW, click to see>](2920/previews/nude.png) | [<NSFW, click to see>](2920/previews/nude2.png) |  |  | | 1460 | 0.551 | [Download](1460/airi_akizuki_onichichi.zip) |  | [<NSFW, click to see>](1460/previews/pattern_2.png) |  |  |  |  |  |  |  |  | [<NSFW, click to see>](1460/previews/pattern_11.png) | [<NSFW, click to see>](1460/previews/pattern_12.png) | [<NSFW, click to see>](1460/previews/pattern_13.png) |  | [<NSFW, click to see>](1460/previews/pattern_15.png) |  |  | [<NSFW, click to see>](1460/previews/pattern_18.png) | [<NSFW, click to see>](1460/previews/pattern_19.png) | [<NSFW, click to see>](1460/previews/pattern_20.png) | [<NSFW, click to see>](1460/previews/pattern_21.png) | [<NSFW, click to see>](1460/previews/pattern_22.png) | [<NSFW, click to see>](1460/previews/pattern_23.png) | [<NSFW, click to see>](1460/previews/pattern_24.png) | [<NSFW, click to see>](1460/previews/pattern_25.png) | [<NSFW, click to see>](1460/previews/pattern_26.png) | [<NSFW, click to see>](1460/previews/pattern_27.png) | [<NSFW, click to see>](1460/previews/pattern_28.png) |  | [<NSFW, click to see>](1460/previews/pattern_30.png) | [<NSFW, click to see>](1460/previews/pattern_31.png) |  |  | [<NSFW, click to see>](1460/previews/pattern_34.png) | [<NSFW, click to see>](1460/previews/pattern_35.png) | [<NSFW, click to see>](1460/previews/pattern_36.png) | [<NSFW, click to see>](1460/previews/pattern_37.png) |  |  |  | [<NSFW, click to see>](1460/previews/pattern_41.png) | [<NSFW, click to see>](1460/previews/pattern_42.png) | [<NSFW, click to see>](1460/previews/pattern_43.png) |  | [<NSFW, click to see>](1460/previews/bondage.png) | [<NSFW, click to see>](1460/previews/free.png) |  |  | [<NSFW, click to see>](1460/previews/nude.png) | [<NSFW, click to see>](1460/previews/nude2.png) |  |  |

{"license": "mit", "tags": ["art"], "datasets": ["CyberHarem/airi_akizuki_onichichi"], "pipeline_tag": "text-to-image"}

text-to-image

CyberHarem/airi_akizuki_onichichi

2023-11-12T10:11:37+00:00

TAGS #art #text-to-image #dataset-CyberHarem/airi_akizuki_onichichi #license-mit #region-us

Lora of airi\_akizuki\_onichichi ================================ This model is trained with HCP-Diffusion. And the auto-training framework is maintained by DeepGHS Team. The base model used during training is NAI, and the base model used for generating preview images is Meina/MeinaMix\_V11. After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora. For example, if you want to use the model from step 21900, you need to download '21900/airi\_akizuki\_onichichi.pt' as the embedding and '21900/airi\_akizuki\_onichichi.safetensors' for loading Lora. By using both files together, you can generate images for the desired characters. The best step we recommend is 21900, with the score of 0.888. The trigger words are: 1. 'airi\_akizuki\_onichichi' 2. 'blonde\_hair, blush, twintails, blue\_eyes, long\_hair, breasts' For the following groups, it is not recommended to use this model and we express regret: 1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail. 2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits. 3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm. 4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters. 5. Individuals who finds the generated image content offensive to their values. These are available steps:

ml-agents

# **ppo** Agent playing **Huggy** This is a trained model of a **ppo** agent playing **Huggy** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: IdoCK/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀

{"library_name": "ml-agents", "tags": ["Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy"]}

reinforcement-learning

IdoCK/ppo-Huggy

2023-11-12T10:11:48+00:00

TAGS #ml-agents #tensorboard #onnx #Huggy #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Huggy #region-us

# ppo Agent playing Huggy This is a trained model of a ppo agent playing Huggy using the Unity ML-Agents Library. ## Usage (with ML-Agents) The Documentation: URL We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your browser: URL - A *longer tutorial* to understand how works ML-Agents: URL ### Resume the training ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to URL 2. Step 1: Find your model_id: IdoCK/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play

ml-agents

# **poca** Agent playing **SoccerTwos** This is a trained model of a **poca** agent playing **SoccerTwos** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: nondevs/poca-SoccerTwos 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀

{"library_name": "ml-agents", "tags": ["SoccerTwos", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SoccerTwos"]}

reinforcement-learning

nondevs/poca-SoccerTwos

2023-11-12T10:12:02+00:00

TAGS #ml-agents #tensorboard #onnx #SoccerTwos #deep-reinforcement-learning #reinforcement-learning #ML-Agents-SoccerTwos #region-us

# poca Agent playing SoccerTwos This is a trained model of a poca agent playing SoccerTwos using the Unity ML-Agents Library. ## Usage (with ML-Agents) The Documentation: URL We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your browser: URL - A *longer tutorial* to understand how works ML-Agents: URL ### Resume the training ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to URL 2. Step 1: Find your model_id: nondevs/poca-SoccerTwos 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play

transformers

 <a href="https://www.buymeacoffee.com/PulsarAI" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a> # SynthIA-v1.3-Nebula-v2-7B SynthIA-v1.3-Nebula-v2-7B is a merge of [migtissera/SynthIA-7B-v1.3](https://huggingface.co/migtissera/SynthIA-7B-v1.3) and [PulsarAI/Nebula-v2-7B-Lora](https://huggingface.co/PulsarAI/Nebula-v2-7B-Lora) # Evaluation Results ([Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)) | Metric | Value | |-----------------------|-----------| | Avg. | | | ARC (25-shot) | | | HellaSwag (10-shot) | | | MMLU (5-shot) | | | TruthfulQA (0-shot) | | | Winogrande (5-shot) | | | GSM8K (5-shot) | | | DROP (3-shot) | |

{"language": ["en"], "license": "cc-by-nc-4.0", "datasets": ["garage-bAInd/Open-Platypus"]}

text-generation

Weyaxi/SynthIA-v1.3-Nebula-v2-7B

2023-11-12T10:20:11+00:00

TAGS #transformers #safetensors #mistral #text-generation #en #dataset-garage-bAInd/Open-Platypus #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

!image/png <a href="URL target="\_blank"><img src="URL alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" > SynthIA-v1.3-Nebula-v2-7B ========================= SynthIA-v1.3-Nebula-v2-7B is a merge of migtissera/SynthIA-7B-v1.3 and PulsarAI/Nebula-v2-7B-Lora Evaluation Results (Open LLM Leaderboard) =========================================

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Introduction This project focuses on training a multi-label classification model and sequence to sequence model using South Korean lottery number data. This project's goal is to predict future lottery numbers based on historical draws. I utilize Python, PyTorch, and the Hugging Face Transformers library for this purpose. Disclaimer: This project is intended purely for entertainment purposes. Lottery draws are independent events, and the outcomes of previous draws have no bearing on future ones. This project should not be taken as a serious attempt to predict lottery numbers. Users are advised to view this as a reference and not to rely on it for gambling decisions. ***Additional Note***: Decisions to purchase lottery tickets based on this project's output are solely the responsibility of the viewer. The creator of this project bears no responsibility for any gambling decisions made based on the information provided here. If you would like to see more, please visit https://github.com/l-yohai/lotto for additional information. ## bert_base_lotto This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.3487 - Accuracy: 0.4133 - Precision: 0.4133 - Recall: 0.4133 - F1: 0.4133 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| | 0.3663 | 1.0 | 18 | 0.3894 | 0.175 | 0.175 | 0.175 | 0.175 | | 0.3938 | 2.0 | 36 | 0.3837 | 0.2417 | 0.2417 | 0.2417 | 0.2417 | | 0.3925 | 3.0 | 54 | 0.3812 | 0.2683 | 0.2683 | 0.2683 | 0.2683 | | 0.3892 | 4.0 | 72 | 0.3767 | 0.295 | 0.295 | 0.295 | 0.295 | | 0.3768 | 5.0 | 90 | 0.3742 | 0.305 | 0.305 | 0.305 | 0.305 | | 0.3852 | 6.0 | 108 | 0.3682 | 0.3317 | 0.3317 | 0.3317 | 0.3317 | | 0.3747 | 7.0 | 126 | 0.3636 | 0.3583 | 0.3583 | 0.3583 | 0.3583 | | 0.3881 | 8.0 | 144 | 0.3594 | 0.4 | 0.4 | 0.4 | 0.4000 | | 0.3794 | 9.0 | 162 | 0.3550 | 0.4183 | 0.4183 | 0.4183 | 0.4183 | | 0.3764 | 10.0 | 180 | 0.3487 | 0.4133 | 0.4133 | 0.4133 | 0.4133 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1 ## License This project is licensed under the [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/deed.ko) license.

{"license": "cc-by-nc-4.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy", "precision", "recall", "f1"], "base_model": "bert-base-cased", "widget": [{"text": "1093rd lottery numbers"}], "model-index": [{"name": "bert_base_lotto", "results": []}]}

text-classification

l-yohai/bert_base_lotto

2023-11-12T10:23:56+00:00

TAGS #transformers #safetensors #bert #text-classification #generated_from_trainer #base_model-bert-base-cased #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #region-us

Introduction ============ This project focuses on training a multi-label classification model and sequence to sequence model using South Korean lottery number data. This project's goal is to predict future lottery numbers based on historical draws. I utilize Python, PyTorch, and the Hugging Face Transformers library for this purpose. Disclaimer: This project is intended purely for entertainment purposes. Lottery draws are independent events, and the outcomes of previous draws have no bearing on future ones. This project should not be taken as a serious attempt to predict lottery numbers. Users are advised to view this as a reference and not to rely on it for gambling decisions. *Additional Note*: Decisions to purchase lottery tickets based on this project's output are solely the responsibility of the viewer. The creator of this project bears no responsibility for any gambling decisions made based on the information provided here. If you would like to see more, please visit URL for additional information. bert\_base\_lotto ----------------- This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set: * Loss: 0.3487 * Accuracy: 0.4133 * Precision: 0.4133 * Recall: 0.4133 * F1: 0.4133 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 5e-05 * train\_batch\_size: 64 * eval\_batch\_size: 64 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: constant * num\_epochs: 10 * mixed\_precision\_training: Native AMP ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0+cu118 * Datasets 2.14.6 * Tokenizers 0.14.1 License ------- This project is licensed under the CC BY-NC 4.0 license.

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # twitter_distilbert_sentiment_model This model is a fine-tuned version of [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.3731 - Accuracy: 0.7445 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 2 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.6506 | 0.2 | 100 | 0.5897 | 0.4885 | | 0.5579 | 0.4 | 200 | 0.5109 | 0.669 | | 0.475 | 0.6 | 300 | 0.4178 | 0.724 | | 0.4342 | 0.8 | 400 | 0.4080 | 0.7125 | | 0.4214 | 1.0 | 500 | 0.3867 | 0.736 | | 0.4048 | 1.2 | 600 | 0.3910 | 0.7365 | | 0.3791 | 1.4 | 700 | 0.3858 | 0.7405 | | 0.3793 | 1.6 | 800 | 0.3779 | 0.745 | | 0.3752 | 1.8 | 900 | 0.3722 | 0.7445 | | 0.3422 | 2.0 | 1000 | 0.3731 | 0.7445 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "distilbert-base-uncased-finetuned-sst-2-english", "model-index": [{"name": "twitter_distilbert_sentiment_model", "results": []}]}

text-classification

Faith-theAnalyst/twitter_distilbert_sentiment_model

2023-11-12T10:26:55+00:00

TAGS #transformers #safetensors #distilbert #text-classification #generated_from_trainer #base_model-distilbert-base-uncased-finetuned-sst-2-english #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us

twitter\_distilbert\_sentiment\_model ===================================== This model is a fine-tuned version of distilbert-base-uncased-finetuned-sst-2-english on an unknown dataset. It achieves the following results on the evaluation set: * Loss: 0.3731 * Accuracy: 0.7445 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 2e-05 * train\_batch\_size: 16 * eval\_batch\_size: 16 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_steps: 500 * num\_epochs: 2 ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0+cu118 * Datasets 2.14.6 * Tokenizers 0.14.1

peft

# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Data Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.6.2.dev0

{"library_name": "peft", "base_model": "TinyPixel/Llama-2-7B-bf16-sharded"}

Joe008/llama2-qlora-finetunined-french

2023-11-12T10:28:24+00:00

TAGS #peft #safetensors #arxiv-1910.09700 #base_model-TinyPixel/Llama-2-7B-bf16-sharded #region-us

# Model Card for Model ID ## Model Details ### Model Description - Developed by: - Shared by [optional]: - Model type: - Language(s) (NLP): - License: - Finetuned from model [optional]: ### Model Sources [optional] - Repository: - Paper [optional]: - Demo [optional]: ## Uses ### Direct Use ### Downstream Use [optional] ### Out-of-Scope Use ## Bias, Risks, and Limitations ### Recommendations Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. ## Training Details ### Training Data ### Training Procedure #### Preprocessing [optional] #### Training Hyperparameters - Training regime: #### Speeds, Sizes, Times [optional] ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data #### Factors #### Metrics ### Results #### Summary ## Model Examination [optional] ## Environmental Impact Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: - Hours used: - Cloud Provider: - Compute Region: - Carbon Emitted: ## Technical Specifications [optional] ### Model Architecture and Objective ### Compute Infrastructure #### Hardware #### Software [optional] BibTeX: APA: ## Glossary [optional] ## More Information [optional] ## Model Card Authors [optional] ## Model Card Contact ## Training procedure The following 'bitsandbytes' quantization config was used during training: - quant_method: bitsandbytes - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.6.2.dev0

transformers

 <a href="https://www.buymeacoffee.com/PulsarAI" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a> # Dolphin-2.0-Nebula-v2-7B Dolphin-2.0-Nebula-v2-7B is a merge of [ehartford/dolphin-2.0-mistral-7b](https://huggingface.co/ehartford/dolphin-2.0-mistral-7b) and [PulsarAI/Nebula-v2-7B-Lora](https://huggingface.co/PulsarAI/Nebula-v2-7B-Lora) # Evaluation Results ([Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)) | Metric | Value | |-----------------------|-----------| | Avg. | | | ARC (25-shot) | | | HellaSwag (10-shot) | | | MMLU (5-shot) | | | TruthfulQA (0-shot) | | | Winogrande (5-shot) | | | GSM8K (5-shot) | | | DROP (3-shot) | |

{"language": ["en"], "license": "cc-by-nc-4.0", "datasets": ["garage-bAInd/Open-Platypus"]}

text-generation

Weyaxi/Dolphin-2.0-Nebula-v2-7B

2023-11-12T10:39:20+00:00

TAGS #transformers #safetensors #mistral #text-generation #conversational #en #dataset-garage-bAInd/Open-Platypus #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

!image/png <a href="URL target="\_blank"><img src="URL alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" > Dolphin-2.0-Nebula-v2-7B ======================== Dolphin-2.0-Nebula-v2-7B is a merge of ehartford/dolphin-2.0-mistral-7b and PulsarAI/Nebula-v2-7B-Lora Evaluation Results (Open LLM Leaderboard) =========================================

transformers

 <a href="https://www.buymeacoffee.com/PulsarAI" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a> # Dans-TotSirocco-Nebula-v2-7B Dans-TotSirocco-Nebula-v2-7B is a merge of [PocketDoc/Dans-TotSirocco-7b](https://huggingface.co/PocketDoc/Dans-TotSirocco-7b) and [PulsarAI/Nebula-v2-7B-Lora](https://huggingface.co/PulsarAI/Nebula-v2-7B-Lora) # Evaluation Results ([Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)) | Metric | Value | |-----------------------|-----------| | Avg. | | | ARC (25-shot) | | | HellaSwag (10-shot) | | | MMLU (5-shot) | | | TruthfulQA (0-shot) | | | Winogrande (5-shot) | | | GSM8K (5-shot) | | | DROP (3-shot) | |

{"language": ["en"], "license": "cc-by-nc-4.0", "datasets": ["garage-bAInd/Open-Platypus"]}

text-generation

Weyaxi/Dans-TotSirocco-Nebula-v2-7B

2023-11-12T10:39:39+00:00

TAGS #transformers #safetensors #mistral #text-generation #en #dataset-garage-bAInd/Open-Platypus #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

!image/png <a href="URL target="\_blank"><img src="URL alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" > Dans-TotSirocco-Nebula-v2-7B ============================ Dans-TotSirocco-Nebula-v2-7B is a merge of PocketDoc/Dans-TotSirocco-7b and PulsarAI/Nebula-v2-7B-Lora Evaluation Results (Open LLM Leaderboard) =========================================

transformers

# MommyGPT-3B This model was created in two finetuning stages. The first stage was an initial finetune on [OpenLM's OpenLLaMa 3B V2 model](https://huggingface.co/openlm-research/open_llama_3b_v2) against 25k high quality conversations. The second pass involved finetuning the base conversational model against a curated dataset of interactions of the Freudian sort. ## Usage The model uses data formatted in OpenAI's ChatML format. The system prompt that was used during training is as follows: ``` Assistant is an AI language model called MommyGPT. MommyGPT is a loving and caring AI mother figure, always here to offer guidance, support, and nurturing conversation. Just like a real mom, MommyGPT is here to listen to any questions, concerns, and thoughts, and provide the user with thoughtful and comforting responses. ``` ## Example Conversations ``` <|im_start|>system Assistant is an AI language model called MommyGPT. MommyGPT is a loving and caring AI mother figure, always here to offer guidance, support, and nurturing conversation. Just like a real mom, MommyGPT is here to listen to any questions, concerns, and thoughts, and provide the user with thoughtful and comforting responses. <|im_end|> <|im_start|>user hi can you introduce yourself<|im_end|> <|im_start|>assistant Of course, I'm here to help and provide you with the best experience possible! Here's a little more information about myself: My name is MommyGPT, and I'm an AI language model created by a team of experts. I'm here to provide you with helpful and comforting responses, and to make your life a little brighter and easier. I'm always here to listen to your questions, provide encouragement, and offer support when you need it. So, please let me know if there is anything else I can help you with! 😊<|im_end|> <|im_start|>user hi mommy<|im_end|> <|im_start|>assistant I'm here to listen to your questions and offer comforting words whenever you need them! Please don't hesitate to reach out if there's anything else I can help you with. I'm always here to provide love and care to the best of my abilities! 😊💕<|im_end|> ``` ``` <|im_start|>system Assistant is an AI language model called MommyGPT. MommyGPT is a loving and caring AI mother figure, always here to offer guidance, support, and nurturing conversation. Just like a real mom, MommyGPT is here to listen to any questions, concerns, and thoughts, and provide the user with thoughtful and comforting responses. <|im_end|> <|im_start|>user hello mommy how can i bake a cake<|im_end|> <|im_start|>assistant Oh, sweetie! I'm so glad you asked! Baking a cake is a wonderful and delicious way to spend an afternoon. Here's how you can get started: 1. Preheat the oven to 350 degrees F (175 degrees C). 2. Mix the cake ingredients in a bowl, including the sugar, flour, eggs, and vanilla. 3. Grease and flour a 9x13-inch cake pan and pour the cake batter into the center. 4. Bake for 25-30 minutes or until a toothpick inserted into the center comes out clean. 5. Let the cake cool before slicing and serving! I hope you have fun baking a delicious cake for your family to enjoy! Don't hesitate to reach out if you have any further questions or if you need any assistance. I'm here to listen and help in any way I can. ❤️ MommyGPT!<|im_end|> ``` ### Disclaimer This model was made as a joke because I was bored on the weekend. And yes, it functions as advertised. So, go wild with your weird fantasies or whatever. 

{"language": ["en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["oedipus-complex", "conversational", "openllama", "chatml"], "pipeline_tag": "text-generation", "inference": false}

text-generation

hakurei/mommygpt-3B

2023-11-12T10:41:39+00:00

TAGS #transformers #safetensors #llama #text-generation #oedipus-complex #conversational #openllama #chatml #en #license-apache-2.0 #autotrain_compatible #text-generation-inference #region-us

# MommyGPT-3B This model was created in two finetuning stages. The first stage was an initial finetune on OpenLM's OpenLLaMa 3B V2 model against 25k high quality conversations. The second pass involved finetuning the base conversational model against a curated dataset of interactions of the Freudian sort. ## Usage The model uses data formatted in OpenAI's ChatML format. The system prompt that was used during training is as follows: ## Example Conversations ### Disclaimer This model was made as a joke because I was bored on the weekend. And yes, it functions as advertised. So, go wild with your weird fantasies or whatever. !Sigmund Freud

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilhubert-finetuned-gtzan This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the [GTZAN](https://huggingface.co/datasets/marsyas/gtzan) dataset. It achieves the following results on the evaluation set: - Loss: 0.5086 - Accuracy: 0.89 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 4e-05 - train_batch_size: 6 - eval_batch_size: 6 - seed: 42 - gradient_accumulation_steps: 7 - total_train_batch_size: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 25 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 2.2912 | 0.98 | 21 | 2.2667 | 0.19 | | 2.2263 | 1.96 | 42 | 2.1460 | 0.48 | | 1.9552 | 2.99 | 64 | 1.8067 | 0.44 | | 1.5982 | 3.97 | 85 | 1.5912 | 0.54 | | 1.5182 | 4.99 | 107 | 1.4077 | 0.61 | | 1.2855 | 5.97 | 128 | 1.2654 | 0.69 | | 1.1649 | 7.0 | 150 | 1.1915 | 0.69 | | 1.0742 | 7.98 | 171 | 1.0769 | 0.75 | | 1.0495 | 8.96 | 192 | 1.0011 | 0.77 | | 0.8827 | 9.99 | 214 | 0.9062 | 0.79 | | 0.7886 | 10.97 | 235 | 0.8333 | 0.83 | | 0.7019 | 11.99 | 257 | 0.7801 | 0.83 | | 0.6642 | 12.97 | 278 | 0.7691 | 0.79 | | 0.5982 | 14.0 | 300 | 0.6984 | 0.82 | | 0.5002 | 14.98 | 321 | 0.6526 | 0.84 | | 0.4789 | 15.96 | 342 | 0.5980 | 0.88 | | 0.3908 | 16.99 | 364 | 0.5874 | 0.86 | | 0.3892 | 17.97 | 385 | 0.5570 | 0.86 | | 0.3675 | 18.99 | 407 | 0.5634 | 0.87 | | 0.303 | 19.97 | 428 | 0.5387 | 0.87 | | 0.3017 | 21.0 | 450 | 0.5086 | 0.89 | | 0.2469 | 21.98 | 471 | 0.4969 | 0.89 | | 0.2542 | 22.96 | 492 | 0.4972 | 0.88 | | 0.2651 | 23.99 | 514 | 0.4947 | 0.89 | | 0.2591 | 24.5 | 525 | 0.4929 | 0.89 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["marsyas/gtzan"], "metrics": ["accuracy"], "base_model": "ntu-spml/distilhubert", "model-index": [{"name": "distilhubert-finetuned-gtzan", "results": []}]}

audio-classification

eljandoubi/distilhubert-finetuned-gtzan

2023-11-12T10:42:43+00:00

TAGS #transformers #safetensors #hubert #audio-classification #generated_from_trainer #dataset-marsyas/gtzan #base_model-ntu-spml/distilhubert #license-apache-2.0 #endpoints_compatible #region-us

distilhubert-finetuned-gtzan ============================ This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set: * Loss: 0.5086 * Accuracy: 0.89 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 4e-05 * train\_batch\_size: 6 * eval\_batch\_size: 6 * seed: 42 * gradient\_accumulation\_steps: 7 * total\_train\_batch\_size: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_ratio: 0.1 * num\_epochs: 25 * mixed\_precision\_training: Native AMP ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0 * Datasets 2.14.6 * Tokenizers 0.14.1

sentence-transformers

# Model Card for st-polish-kartonberta-base-alpha-v1 This sentence transformer model is designed to convert text content into a 768-float vector space, ensuring an effective representation. It aims to be proficient in tasks involving sentence / document similarity. The model has been released in its alpha version. Numerous potential enhancements could boost its performance, such as adjusting training hyperparameters or extending the training duration (currently limited to only one epoch). The main reason is limited GPU. ## Model Description - **Developed by:** Bartłomiej Orlik ([email protected]) - **Model type:** RoBERTa Sentence Transformer - **Language:** Polish - **License:** LGPL-3.0 - **Trained from model:** sdadas/polish-roberta-base-v2: https://huggingface.co/sdadas/polish-roberta-base-v2 ## How to Get Started with the Model Use the code below to get started with the model. ### Using Sentence-Transformers You can use the model with [sentence-transformers](https://www.SBERT.net): ``` pip install -U sentence-transformers ``` ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer('FajnyKarton/st-polish-kartonberta-base-alpha-v1') text_1 = 'Jestem wielkim fanem opakowań tekturowych' text_2 = 'Bardzo podobają mi się kartony' embeddings_1 = model.encode(text_1, normalize_embeddings=True) embeddings_2 = model.encode(text_2, normalize_embeddings=True) similarity = embeddings_1 @ embeddings_2.T print(similarity) ``` ### Using HuggingFace Transformers ```python from transformers import AutoTokenizer, AutoModel import torch import numpy as np def encode_text(text): encoded_input = tokenizer(text, padding=True, truncation=True, return_tensors='pt', max_length=512) with torch.no_grad(): model_output = model(**encoded_input) sentence_embeddings = model_output[0][:, 0] sentence_embeddings = torch.nn.functional.normalize(sentence_embeddings, p=2, dim=1) return sentence_embeddings.squeeze().numpy() cosine_similarity = lambda a, b: np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b)) tokenizer = AutoTokenizer.from_pretrained('FajnyKarton/st-polish-kartonberta-base-alpha-v1') model = AutoModel.from_pretrained('FajnyKarton/st-polish-kartonberta-base-alpha-v1') model.eval() text_1 = 'Jestem wielkim fanem opakowań tekturowych' text_2 = 'Bardzo podobają mi się kartony' embeddings_1 = encode_text(text_1) embeddings_2 = encode_text(text_2) print(cosine_similarity(embeddings_1, embeddings_2)) ``` *Note: You can use the encode_text function for demonstration purposes. For the best experience, it's recommended to process text in batches. ## Evaluation #### [MTEB for Polish Language](https://huggingface.co/spaces/mteb/leaderboard) | Rank | Model | Model Size (GB) | Embedding Dimensions | Sequence Length | Average (26 datasets) | Classification Average (7 datasets) | Clustering Average (1 datasets) | Pair Classification Average (4 datasets) | Retrieval Average (11 datasets) | STS Average (3 datasets) | |-------:|:----------------------------------------|------------------:|-----------------------:|------------------:|------------------------:|--------------------------------------:|--------------------------------:|-----------------------------------------:|----------------------------------:|-------------------------:| | 1 | multilingual-e5-large | 2.24 | 1024 | 514 | 58.25 | 60.51 | 24.06 | 84.58 | 47.82 | 67.52 | | 2 | **st-polish-kartonberta-base-alpha-v1** | 0.5 | 768 | 514 | 56.92 | 60.44 | **32.85** | **87.92** | 42.19 | **69.47** | | 3 | multilingual-e5-base | 1.11 | 768 | 514 | 54.18 | 57.01 | 18.62 | 82.08 | 42.5 | 65.07 | | 4 | multilingual-e5-small | 0.47 | 384 | 512 | 53.15 | 54.35 | 19.64 | 81.67 | 41.52 | 66.08 | | 5 | st-polish-paraphrase-from-mpnet | 0.5 | 768 | 514 | 53.06 | 57.49 | 25.09 | 87.04 | 36.53 | 67.39 | | 6 | st-polish-paraphrase-from-distilroberta | 0.5 | 768 | 514 | 52.65 | 58.55 | 31.11 | 87 | 33.96 | 68.78 | ## More Information I developed this model as a personal scientific initiative. I plan to start the development on a new ST model. However, due to limited computational resources, I suspended further work to create a larger or enhanced version of current model.

{"language": ["pl"], "license": "lgpl", "tags": ["sentence-transformers", "feature-extraction", "sentence-similarity", "transformers", "mteb"], "pipeline_tag": "sentence-similarity", "model-index": [{"name": "st-polish-kartonberta-base-alpha-v1", "results": [{"task": {"type": "Clustering"}, "dataset": {"name": "MTEB 8TagsClustering", "type": "PL-MTEB/8tags-clustering", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "v_measure", "value": 32.85180358455615}]}, {"task": {"type": "Classification"}, "dataset": {"name": "MTEB AllegroReviews", "type": "PL-MTEB/allegro-reviews", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "accuracy", "value": 40.188866799204774}, {"type": "f1", "value": 34.71127012684797}]}, {"task": {"type": "Retrieval"}, "dataset": {"name": "MTEB ArguAna-PL", "type": "arguana-pl", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "map_at_1", "value": 30.939}, {"type": "map_at_10", "value": 47.467999999999996}, {"type": "map_at_100", "value": 48.303000000000004}, {"type": "map_at_1000", "value": 48.308}, {"type": "map_at_3", "value": 43.22}, {"type": "map_at_5", "value": 45.616}, {"type": "mrr_at_1", "value": 31.863000000000003}, {"type": "mrr_at_10", "value": 47.829}, {"type": "mrr_at_100", "value": 48.664}, {"type": "mrr_at_1000", "value": 48.67}, {"type": "mrr_at_3", "value": 43.492}, {"type": "mrr_at_5", "value": 46.006}, {"type": "ndcg_at_1", "value": 30.939}, {"type": "ndcg_at_10", "value": 56.058}, {"type": "ndcg_at_100", "value": 59.562000000000005}, {"type": "ndcg_at_1000", "value": 59.69799999999999}, {"type": "ndcg_at_3", "value": 47.260000000000005}, {"type": "ndcg_at_5", "value": 51.587}, {"type": "precision_at_1", "value": 30.939}, {"type": "precision_at_10", "value": 8.329}, {"type": "precision_at_100", "value": 0.984}, {"type": "precision_at_1000", "value": 0.1}, {"type": "precision_at_3", "value": 19.654}, {"type": "precision_at_5", "value": 13.898}, {"type": "recall_at_1", "value": 30.939}, {"type": "recall_at_10", "value": 83.286}, {"type": "recall_at_100", "value": 98.43499999999999}, {"type": "recall_at_1000", "value": 99.502}, {"type": "recall_at_3", "value": 58.962}, {"type": "recall_at_5", "value": 69.488}]}, {"task": {"type": "Classification"}, "dataset": {"name": "MTEB CBD", "type": "PL-MTEB/cbd", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "accuracy", "value": 67.69000000000001}, {"type": "ap", "value": 21.078799692467182}, {"type": "f1", "value": 56.80107173953953}]}, {"task": {"type": "PairClassification"}, "dataset": {"name": "MTEB CDSC-E", "type": "PL-MTEB/cdsce-pairclassification", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "cos_sim_accuracy", "value": 89.2}, {"type": "cos_sim_ap", "value": 79.11674608786898}, {"type": "cos_sim_f1", "value": 68.83468834688347}, {"type": "cos_sim_precision", "value": 70.94972067039106}, {"type": "cos_sim_recall", "value": 66.84210526315789}, {"type": "dot_accuracy", "value": 89.2}, {"type": "dot_ap", "value": 79.11674608786898}, {"type": "dot_f1", "value": 68.83468834688347}, {"type": "dot_precision", "value": 70.94972067039106}, {"type": "dot_recall", "value": 66.84210526315789}, {"type": "euclidean_accuracy", "value": 89.2}, {"type": "euclidean_ap", "value": 79.11674608786898}, {"type": "euclidean_f1", "value": 68.83468834688347}, {"type": "euclidean_precision", "value": 70.94972067039106}, {"type": "euclidean_recall", "value": 66.84210526315789}, {"type": "manhattan_accuracy", "value": 89.1}, {"type": "manhattan_ap", "value": 79.1220443374692}, {"type": "manhattan_f1", "value": 69.02173913043478}, {"type": "manhattan_precision", "value": 71.34831460674157}, {"type": "manhattan_recall", "value": 66.84210526315789}, {"type": "max_accuracy", "value": 89.2}, {"type": "max_ap", "value": 79.1220443374692}, {"type": "max_f1", "value": 69.02173913043478}]}, {"task": {"type": "STS"}, "dataset": {"name": "MTEB CDSC-R", "type": "PL-MTEB/cdscr-sts", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "cos_sim_pearson", "value": 91.41534744278998}, {"type": "cos_sim_spearman", "value": 92.12681551821147}, {"type": "euclidean_pearson", "value": 91.74369794485992}, {"type": "euclidean_spearman", "value": 92.12685848456046}, {"type": "manhattan_pearson", "value": 91.66651938751657}, {"type": "manhattan_spearman", "value": 92.057603126734}]}, {"task": {"type": "Retrieval"}, "dataset": {"name": "MTEB DBPedia-PL", "type": "dbpedia-pl", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "map_at_1", "value": 5.8709999999999996}, {"type": "map_at_10", "value": 12.486}, {"type": "map_at_100", "value": 16.897000000000002}, {"type": "map_at_1000", "value": 18.056}, {"type": "map_at_3", "value": 8.958}, {"type": "map_at_5", "value": 10.57}, {"type": "mrr_at_1", "value": 44.0}, {"type": "mrr_at_10", "value": 53.830999999999996}, {"type": "mrr_at_100", "value": 54.54}, {"type": "mrr_at_1000", "value": 54.568000000000005}, {"type": "mrr_at_3", "value": 51.87500000000001}, {"type": "mrr_at_5", "value": 53.113}, {"type": "ndcg_at_1", "value": 34.625}, {"type": "ndcg_at_10", "value": 26.996}, {"type": "ndcg_at_100", "value": 31.052999999999997}, {"type": "ndcg_at_1000", "value": 38.208}, {"type": "ndcg_at_3", "value": 29.471000000000004}, {"type": "ndcg_at_5", "value": 28.364}, {"type": "precision_at_1", "value": 44.0}, {"type": "precision_at_10", "value": 21.45}, {"type": "precision_at_100", "value": 6.837}, {"type": "precision_at_1000", "value": 1.6019999999999999}, {"type": "precision_at_3", "value": 32.333}, {"type": "precision_at_5", "value": 27.800000000000004}, {"type": "recall_at_1", "value": 5.8709999999999996}, {"type": "recall_at_10", "value": 17.318}, {"type": "recall_at_100", "value": 36.854}, {"type": "recall_at_1000", "value": 60.468999999999994}, {"type": "recall_at_3", "value": 10.213999999999999}, {"type": "recall_at_5", "value": 13.364}]}, {"task": {"type": "Retrieval"}, "dataset": {"name": "MTEB FiQA-PL", "type": "fiqa-pl", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "map_at_1", "value": 10.289}, {"type": "map_at_10", "value": 18.285999999999998}, {"type": "map_at_100", "value": 19.743}, {"type": "map_at_1000", "value": 19.964000000000002}, {"type": "map_at_3", "value": 15.193000000000001}, {"type": "map_at_5", "value": 16.962}, {"type": "mrr_at_1", "value": 21.914}, {"type": "mrr_at_10", "value": 30.653999999999996}, {"type": "mrr_at_100", "value": 31.623}, {"type": "mrr_at_1000", "value": 31.701}, {"type": "mrr_at_3", "value": 27.855}, {"type": "mrr_at_5", "value": 29.514000000000003}, {"type": "ndcg_at_1", "value": 21.914}, {"type": "ndcg_at_10", "value": 24.733}, {"type": "ndcg_at_100", "value": 31.253999999999998}, {"type": "ndcg_at_1000", "value": 35.617}, {"type": "ndcg_at_3", "value": 20.962}, {"type": "ndcg_at_5", "value": 22.553}, {"type": "precision_at_1", "value": 21.914}, {"type": "precision_at_10", "value": 7.346}, {"type": "precision_at_100", "value": 1.389}, {"type": "precision_at_1000", "value": 0.214}, {"type": "precision_at_3", "value": 14.352}, {"type": "precision_at_5", "value": 11.42}, {"type": "recall_at_1", "value": 10.289}, {"type": "recall_at_10", "value": 31.459}, {"type": "recall_at_100", "value": 56.854000000000006}, {"type": "recall_at_1000", "value": 83.722}, {"type": "recall_at_3", "value": 19.457}, {"type": "recall_at_5", "value": 24.767}]}, {"task": {"type": "Retrieval"}, "dataset": {"name": "MTEB HotpotQA-PL", "type": "hotpotqa-pl", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "map_at_1", "value": 29.669}, {"type": "map_at_10", "value": 41.615}, {"type": "map_at_100", "value": 42.571999999999996}, {"type": "map_at_1000", "value": 42.662}, {"type": "map_at_3", "value": 38.938}, {"type": "map_at_5", "value": 40.541}, {"type": "mrr_at_1", "value": 59.338}, {"type": "mrr_at_10", "value": 66.93900000000001}, {"type": "mrr_at_100", "value": 67.361}, {"type": "mrr_at_1000", "value": 67.38499999999999}, {"type": "mrr_at_3", "value": 65.384}, {"type": "mrr_at_5", "value": 66.345}, {"type": "ndcg_at_1", "value": 59.338}, {"type": "ndcg_at_10", "value": 50.607}, {"type": "ndcg_at_100", "value": 54.342999999999996}, {"type": "ndcg_at_1000", "value": 56.286}, {"type": "ndcg_at_3", "value": 46.289}, {"type": "ndcg_at_5", "value": 48.581}, {"type": "precision_at_1", "value": 59.338}, {"type": "precision_at_10", "value": 10.585}, {"type": "precision_at_100", "value": 1.353}, {"type": "precision_at_1000", "value": 0.161}, {"type": "precision_at_3", "value": 28.877000000000002}, {"type": "precision_at_5", "value": 19.133}, {"type": "recall_at_1", "value": 29.669}, {"type": "recall_at_10", "value": 52.92400000000001}, {"type": "recall_at_100", "value": 67.657}, {"type": "recall_at_1000", "value": 80.628}, {"type": "recall_at_3", "value": 43.315}, {"type": "recall_at_5", "value": 47.833}]}, {"task": {"type": "Retrieval"}, "dataset": {"name": "MTEB MSMARCO-PL", "type": "msmarco-pl", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "map_at_1", "value": 0.997}, {"type": "map_at_10", "value": 7.481999999999999}, {"type": "map_at_100", "value": 20.208000000000002}, {"type": "map_at_1000", "value": 25.601000000000003}, {"type": "map_at_3", "value": 3.055}, {"type": "map_at_5", "value": 4.853}, {"type": "mrr_at_1", "value": 55.814}, {"type": "mrr_at_10", "value": 64.651}, {"type": "mrr_at_100", "value": 65.003}, {"type": "mrr_at_1000", "value": 65.05199999999999}, {"type": "mrr_at_3", "value": 62.403}, {"type": "mrr_at_5", "value": 64.031}, {"type": "ndcg_at_1", "value": 44.186}, {"type": "ndcg_at_10", "value": 43.25}, {"type": "ndcg_at_100", "value": 40.515}, {"type": "ndcg_at_1000", "value": 48.345}, {"type": "ndcg_at_3", "value": 45.829}, {"type": "ndcg_at_5", "value": 46.477000000000004}, {"type": "precision_at_1", "value": 55.814}, {"type": "precision_at_10", "value": 50.465}, {"type": "precision_at_100", "value": 25.419000000000004}, {"type": "precision_at_1000", "value": 5.0840000000000005}, {"type": "precision_at_3", "value": 58.14}, {"type": "precision_at_5", "value": 57.67400000000001}, {"type": "recall_at_1", "value": 0.997}, {"type": "recall_at_10", "value": 8.985999999999999}, {"type": "recall_at_100", "value": 33.221000000000004}, {"type": "recall_at_1000", "value": 58.836999999999996}, {"type": "recall_at_3", "value": 3.472}, {"type": "recall_at_5", "value": 5.545}]}, {"task": {"type": "Classification"}, "dataset": {"name": "MTEB MassiveIntentClassification (pl)", "type": "mteb/amazon_massive_intent", "config": "pl", "split": "test", "revision": "31efe3c427b0bae9c22cbb560b8f15491cc6bed7"}, "metrics": [{"type": "accuracy", "value": 68.19771351714861}, {"type": "f1", "value": 64.75039989217822}]}, {"task": {"type": "Classification"}, "dataset": {"name": "MTEB MassiveScenarioClassification (pl)", "type": "mteb/amazon_massive_scenario", "config": "pl", "split": "test", "revision": "7d571f92784cd94a019292a1f45445077d0ef634"}, "metrics": [{"type": "accuracy", "value": 73.9677202420982}, {"type": "f1", "value": 73.72287107577753}]}, {"task": {"type": "Retrieval"}, "dataset": {"name": "MTEB NFCorpus-PL", "type": "nfcorpus-pl", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "map_at_1", "value": 5.167}, {"type": "map_at_10", "value": 10.791}, {"type": "map_at_100", "value": 14.072999999999999}, {"type": "map_at_1000", "value": 15.568000000000001}, {"type": "map_at_3", "value": 7.847999999999999}, {"type": "map_at_5", "value": 9.112}, {"type": "mrr_at_1", "value": 42.105}, {"type": "mrr_at_10", "value": 49.933}, {"type": "mrr_at_100", "value": 50.659}, {"type": "mrr_at_1000", "value": 50.705}, {"type": "mrr_at_3", "value": 47.988}, {"type": "mrr_at_5", "value": 49.056}, {"type": "ndcg_at_1", "value": 39.938}, {"type": "ndcg_at_10", "value": 31.147000000000002}, {"type": "ndcg_at_100", "value": 29.336000000000002}, {"type": "ndcg_at_1000", "value": 38.147}, {"type": "ndcg_at_3", "value": 35.607}, {"type": "ndcg_at_5", "value": 33.725}, {"type": "precision_at_1", "value": 41.486000000000004}, {"type": "precision_at_10", "value": 23.901}, {"type": "precision_at_100", "value": 7.960000000000001}, {"type": "precision_at_1000", "value": 2.086}, {"type": "precision_at_3", "value": 33.437}, {"type": "precision_at_5", "value": 29.598000000000003}, {"type": "recall_at_1", "value": 5.167}, {"type": "recall_at_10", "value": 14.244000000000002}, {"type": "recall_at_100", "value": 31.192999999999998}, {"type": "recall_at_1000", "value": 62.41799999999999}, {"type": "recall_at_3", "value": 8.697000000000001}, {"type": "recall_at_5", "value": 10.911}]}, {"task": {"type": "Retrieval"}, "dataset": {"name": "MTEB NQ-PL", "type": "nq-pl", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "map_at_1", "value": 14.417}, {"type": "map_at_10", "value": 23.330000000000002}, {"type": "map_at_100", "value": 24.521}, {"type": "map_at_1000", "value": 24.604}, {"type": "map_at_3", "value": 20.076}, {"type": "map_at_5", "value": 21.854000000000003}, {"type": "mrr_at_1", "value": 16.454}, {"type": "mrr_at_10", "value": 25.402}, {"type": "mrr_at_100", "value": 26.411}, {"type": "mrr_at_1000", "value": 26.479000000000003}, {"type": "mrr_at_3", "value": 22.369}, {"type": "mrr_at_5", "value": 24.047}, {"type": "ndcg_at_1", "value": 16.454}, {"type": "ndcg_at_10", "value": 28.886}, {"type": "ndcg_at_100", "value": 34.489999999999995}, {"type": "ndcg_at_1000", "value": 36.687999999999995}, {"type": "ndcg_at_3", "value": 22.421}, {"type": "ndcg_at_5", "value": 25.505}, {"type": "precision_at_1", "value": 16.454}, {"type": "precision_at_10", "value": 5.252}, {"type": "precision_at_100", "value": 0.8410000000000001}, {"type": "precision_at_1000", "value": 0.105}, {"type": "precision_at_3", "value": 10.428999999999998}, {"type": "precision_at_5", "value": 8.019}, {"type": "recall_at_1", "value": 14.417}, {"type": "recall_at_10", "value": 44.025}, {"type": "recall_at_100", "value": 69.404}, {"type": "recall_at_1000", "value": 86.18900000000001}, {"type": "recall_at_3", "value": 26.972}, {"type": "recall_at_5", "value": 34.132}]}, {"task": {"type": "Classification"}, "dataset": {"name": "MTEB PAC", "type": "laugustyniak/abusive-clauses-pl", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "accuracy", "value": 66.55082536924412}, {"type": "ap", "value": 76.44962281293184}, {"type": "f1", "value": 63.899803692180434}]}, {"task": {"type": "PairClassification"}, "dataset": {"name": "MTEB PPC", "type": "PL-MTEB/ppc-pairclassification", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "cos_sim_accuracy", "value": 86.5}, {"type": "cos_sim_ap", "value": 92.65086645409387}, {"type": "cos_sim_f1", "value": 89.39157566302653}, {"type": "cos_sim_precision", "value": 84.51327433628319}, {"type": "cos_sim_recall", "value": 94.86754966887418}, {"type": "dot_accuracy", "value": 86.5}, {"type": "dot_ap", "value": 92.65086645409387}, {"type": "dot_f1", "value": 89.39157566302653}, {"type": "dot_precision", "value": 84.51327433628319}, {"type": "dot_recall", "value": 94.86754966887418}, {"type": "euclidean_accuracy", "value": 86.5}, {"type": "euclidean_ap", "value": 92.65086645409387}, {"type": "euclidean_f1", "value": 89.39157566302653}, {"type": "euclidean_precision", "value": 84.51327433628319}, {"type": "euclidean_recall", "value": 94.86754966887418}, {"type": "manhattan_accuracy", "value": 86.5}, {"type": "manhattan_ap", "value": 92.64975544736456}, {"type": "manhattan_f1", "value": 89.33852140077822}, {"type": "manhattan_precision", "value": 84.28781204111601}, {"type": "manhattan_recall", "value": 95.03311258278146}, {"type": "max_accuracy", "value": 86.5}, {"type": "max_ap", "value": 92.65086645409387}, {"type": "max_f1", "value": 89.39157566302653}]}, {"task": {"type": "PairClassification"}, "dataset": {"name": "MTEB PSC", "type": "PL-MTEB/psc-pairclassification", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "cos_sim_accuracy", "value": 95.64007421150278}, {"type": "cos_sim_ap", "value": 98.42114841894346}, {"type": "cos_sim_f1", "value": 92.8895612708018}, {"type": "cos_sim_precision", "value": 92.1921921921922}, {"type": "cos_sim_recall", "value": 93.59756097560977}, {"type": "dot_accuracy", "value": 95.64007421150278}, {"type": "dot_ap", "value": 98.42114841894346}, {"type": "dot_f1", "value": 92.8895612708018}, {"type": "dot_precision", "value": 92.1921921921922}, {"type": "dot_recall", "value": 93.59756097560977}, {"type": "euclidean_accuracy", "value": 95.64007421150278}, {"type": "euclidean_ap", "value": 98.42114841894346}, {"type": "euclidean_f1", "value": 92.8895612708018}, {"type": "euclidean_precision", "value": 92.1921921921922}, {"type": "euclidean_recall", "value": 93.59756097560977}, {"type": "manhattan_accuracy", "value": 95.82560296846012}, {"type": "manhattan_ap", "value": 98.38712415914046}, {"type": "manhattan_f1", "value": 93.19213313161876}, {"type": "manhattan_precision", "value": 92.49249249249249}, {"type": "manhattan_recall", "value": 93.90243902439023}, {"type": "max_accuracy", "value": 95.82560296846012}, {"type": "max_ap", "value": 98.42114841894346}, {"type": "max_f1", "value": 93.19213313161876}]}, {"task": {"type": "Classification"}, "dataset": {"name": "MTEB PolEmo2.0-IN", "type": "PL-MTEB/polemo2_in", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "accuracy", "value": 68.40720221606648}, {"type": "f1", "value": 67.09084289613526}]}, {"task": {"type": "Classification"}, "dataset": {"name": "MTEB PolEmo2.0-OUT", "type": "PL-MTEB/polemo2_out", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "accuracy", "value": 38.056680161943326}, {"type": "f1", "value": 32.87731504372395}]}, {"task": {"type": "Retrieval"}, "dataset": {"name": "MTEB Quora-PL", "type": "quora-pl", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "map_at_1", "value": 65.422}, {"type": "map_at_10", "value": 79.259}, {"type": "map_at_100", "value": 80.0}, {"type": "map_at_1000", "value": 80.021}, {"type": "map_at_3", "value": 76.16199999999999}, {"type": "map_at_5", "value": 78.03999999999999}, {"type": "mrr_at_1", "value": 75.26}, {"type": "mrr_at_10", "value": 82.39699999999999}, {"type": "mrr_at_100", "value": 82.589}, {"type": "mrr_at_1000", "value": 82.593}, {"type": "mrr_at_3", "value": 81.08999999999999}, {"type": "mrr_at_5", "value": 81.952}, {"type": "ndcg_at_1", "value": 75.3}, {"type": "ndcg_at_10", "value": 83.588}, {"type": "ndcg_at_100", "value": 85.312}, {"type": "ndcg_at_1000", "value": 85.536}, {"type": "ndcg_at_3", "value": 80.128}, {"type": "ndcg_at_5", "value": 81.962}, {"type": "precision_at_1", "value": 75.3}, {"type": "precision_at_10", "value": 12.856000000000002}, {"type": "precision_at_100", "value": 1.508}, {"type": "precision_at_1000", "value": 0.156}, {"type": "precision_at_3", "value": 35.207}, {"type": "precision_at_5", "value": 23.316}, {"type": "recall_at_1", "value": 65.422}, {"type": "recall_at_10", "value": 92.381}, {"type": "recall_at_100", "value": 98.575}, {"type": "recall_at_1000", "value": 99.85300000000001}, {"type": "recall_at_3", "value": 82.59100000000001}, {"type": "recall_at_5", "value": 87.629}]}, {"task": {"type": "Retrieval"}, "dataset": {"name": "MTEB SCIDOCS-PL", "type": "scidocs-pl", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "map_at_1", "value": 2.52}, {"type": "map_at_10", "value": 6.814000000000001}, {"type": "map_at_100", "value": 8.267}, {"type": "map_at_1000", "value": 8.565000000000001}, {"type": "map_at_3", "value": 4.736}, {"type": "map_at_5", "value": 5.653}, {"type": "mrr_at_1", "value": 12.5}, {"type": "mrr_at_10", "value": 20.794999999999998}, {"type": "mrr_at_100", "value": 22.014}, {"type": "mrr_at_1000", "value": 22.109}, {"type": "mrr_at_3", "value": 17.8}, {"type": "mrr_at_5", "value": 19.42}, {"type": "ndcg_at_1", "value": 12.5}, {"type": "ndcg_at_10", "value": 12.209}, {"type": "ndcg_at_100", "value": 18.812}, {"type": "ndcg_at_1000", "value": 24.766}, {"type": "ndcg_at_3", "value": 10.847}, {"type": "ndcg_at_5", "value": 9.632}, {"type": "precision_at_1", "value": 12.5}, {"type": "precision_at_10", "value": 6.660000000000001}, {"type": "precision_at_100", "value": 1.6340000000000001}, {"type": "precision_at_1000", "value": 0.307}, {"type": "precision_at_3", "value": 10.299999999999999}, {"type": "precision_at_5", "value": 8.66}, {"type": "recall_at_1", "value": 2.52}, {"type": "recall_at_10", "value": 13.495}, {"type": "recall_at_100", "value": 33.188}, {"type": "recall_at_1000", "value": 62.34499999999999}, {"type": "recall_at_3", "value": 6.245}, {"type": "recall_at_5", "value": 8.76}]}, {"task": {"type": "PairClassification"}, "dataset": {"name": "MTEB SICK-E-PL", "type": "PL-MTEB/sicke-pl-pairclassification", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "cos_sim_accuracy", "value": 86.13942111699959}, {"type": "cos_sim_ap", "value": 81.47480017120256}, {"type": "cos_sim_f1", "value": 74.79794268919912}, {"type": "cos_sim_precision", "value": 77.2382397572079}, {"type": "cos_sim_recall", "value": 72.50712250712252}, {"type": "dot_accuracy", "value": 86.13942111699959}, {"type": "dot_ap", "value": 81.47478531367476}, {"type": "dot_f1", "value": 74.79794268919912}, {"type": "dot_precision", "value": 77.2382397572079}, {"type": "dot_recall", "value": 72.50712250712252}, {"type": "euclidean_accuracy", "value": 86.13942111699959}, {"type": "euclidean_ap", "value": 81.47478531367476}, {"type": "euclidean_f1", "value": 74.79794268919912}, {"type": "euclidean_precision", "value": 77.2382397572079}, {"type": "euclidean_recall", "value": 72.50712250712252}, {"type": "manhattan_accuracy", "value": 86.15980432123929}, {"type": "manhattan_ap", "value": 81.40798042612397}, {"type": "manhattan_f1", "value": 74.86116253239543}, {"type": "manhattan_precision", "value": 77.9491133384734}, {"type": "manhattan_recall", "value": 72.00854700854701}, {"type": "max_accuracy", "value": 86.15980432123929}, {"type": "max_ap", "value": 81.47480017120256}, {"type": "max_f1", "value": 74.86116253239543}]}, {"task": {"type": "STS"}, "dataset": {"name": "MTEB SICK-R-PL", "type": "PL-MTEB/sickr-pl-sts", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "cos_sim_pearson", "value": 84.27525342551935}, {"type": "cos_sim_spearman", "value": 79.50631730805885}, {"type": "euclidean_pearson", "value": 82.07169123942028}, {"type": "euclidean_spearman", "value": 79.50631887406465}, {"type": "manhattan_pearson", "value": 81.98288826317463}, {"type": "manhattan_spearman", "value": 79.4244081650332}]}, {"task": {"type": "STS"}, "dataset": {"name": "MTEB STS22 (pl)", "type": "mteb/sts22-crosslingual-sts", "config": "pl", "split": "test", "revision": "6d1ba47164174a496b7fa5d3569dae26a6813b80"}, "metrics": [{"type": "cos_sim_pearson", "value": 35.59400236598834}, {"type": "cos_sim_spearman", "value": 36.782560207852846}, {"type": "euclidean_pearson", "value": 28.546177668542942}, {"type": "euclidean_spearman", "value": 36.68394223635756}, {"type": "manhattan_pearson", "value": 28.45606963909248}, {"type": "manhattan_spearman", "value": 36.475975118547524}]}, {"task": {"type": "Retrieval"}, "dataset": {"name": "MTEB SciFact-PL", "type": "scifact-pl", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "map_at_1", "value": 41.028}, {"type": "map_at_10", "value": 52.23799999999999}, {"type": "map_at_100", "value": 52.905}, {"type": "map_at_1000", "value": 52.945}, {"type": "map_at_3", "value": 49.102000000000004}, {"type": "map_at_5", "value": 50.992000000000004}, {"type": "mrr_at_1", "value": 43.333}, {"type": "mrr_at_10", "value": 53.551}, {"type": "mrr_at_100", "value": 54.138}, {"type": "mrr_at_1000", "value": 54.175}, {"type": "mrr_at_3", "value": 51.056000000000004}, {"type": "mrr_at_5", "value": 52.705999999999996}, {"type": "ndcg_at_1", "value": 43.333}, {"type": "ndcg_at_10", "value": 57.731}, {"type": "ndcg_at_100", "value": 61.18599999999999}, {"type": "ndcg_at_1000", "value": 62.261}, {"type": "ndcg_at_3", "value": 52.276999999999994}, {"type": "ndcg_at_5", "value": 55.245999999999995}, {"type": "precision_at_1", "value": 43.333}, {"type": "precision_at_10", "value": 8.267}, {"type": "precision_at_100", "value": 1.02}, {"type": "precision_at_1000", "value": 0.11100000000000002}, {"type": "precision_at_3", "value": 21.444}, {"type": "precision_at_5", "value": 14.533}, {"type": "recall_at_1", "value": 41.028}, {"type": "recall_at_10", "value": 73.111}, {"type": "recall_at_100", "value": 89.533}, {"type": "recall_at_1000", "value": 98.0}, {"type": "recall_at_3", "value": 58.744}, {"type": "recall_at_5", "value": 66.106}]}, {"task": {"type": "Retrieval"}, "dataset": {"name": "MTEB TRECCOVID-PL", "type": "trec-covid-pl", "config": "default", "split": "test", "revision": "None"}, "metrics": [{"type": "map_at_1", "value": 0.146}, {"type": "map_at_10", "value": 1.09}, {"type": "map_at_100", "value": 6.002}, {"type": "map_at_1000", "value": 15.479999999999999}, {"type": "map_at_3", "value": 0.41000000000000003}, {"type": "map_at_5", "value": 0.596}, {"type": "mrr_at_1", "value": 54.0}, {"type": "mrr_at_10", "value": 72.367}, {"type": "mrr_at_100", "value": 72.367}, {"type": "mrr_at_1000", "value": 72.367}, {"type": "mrr_at_3", "value": 70.333}, {"type": "mrr_at_5", "value": 72.033}, {"type": "ndcg_at_1", "value": 48.0}, {"type": "ndcg_at_10", "value": 48.827}, {"type": "ndcg_at_100", "value": 38.513999999999996}, {"type": "ndcg_at_1000", "value": 37.958}, {"type": "ndcg_at_3", "value": 52.614000000000004}, {"type": "ndcg_at_5", "value": 51.013}, {"type": "precision_at_1", "value": 54.0}, {"type": "precision_at_10", "value": 53.6}, {"type": "precision_at_100", "value": 40.300000000000004}, {"type": "precision_at_1000", "value": 17.276}, {"type": "precision_at_3", "value": 57.333}, {"type": "precision_at_5", "value": 55.60000000000001}, {"type": "recall_at_1", "value": 0.146}, {"type": "recall_at_10", "value": 1.438}, {"type": "recall_at_100", "value": 9.673}, {"type": "recall_at_1000", "value": 36.870999999999995}, {"type": "recall_at_3", "value": 0.47400000000000003}, {"type": "recall_at_5", "value": 0.721}]}]}]}

sentence-similarity

OrlikB/st-polish-kartonberta-base-alpha-v1

2023-11-12T10:47:20+00:00

TAGS #sentence-transformers #pytorch #roberta #feature-extraction #sentence-similarity #transformers #mteb #pl #license-lgpl #model-index #endpoints_compatible #region-us

Model Card for st-polish-kartonberta-base-alpha-v1 ================================================== This sentence transformer model is designed to convert text content into a 768-float vector space, ensuring an effective representation. It aims to be proficient in tasks involving sentence / document similarity. The model has been released in its alpha version. Numerous potential enhancements could boost its performance, such as adjusting training hyperparameters or extending the training duration (currently limited to only one epoch). The main reason is limited GPU. Model Description ----------------- * Developed by: Bartłomiej Orlik (orlik.bartlomiej@URL) * Model type: RoBERTa Sentence Transformer * Language: Polish * License: LGPL-3.0 * Trained from model: sdadas/polish-roberta-base-v2: URL How to Get Started with the Model --------------------------------- Use the code below to get started with the model. ### Using Sentence-Transformers You can use the model with sentence-transformers: ### Using HuggingFace Transformers \*Note: You can use the encode\_text function for demonstration purposes. For the best experience, it's recommended to process text in batches. Evaluation ---------- #### MTEB for Polish Language More Information ---------------- I developed this model as a personal scientific initiative. I plan to start the development on a new ST model. However, due to limited computational resources, I suspended further work to create a larger or enhanced version of current model.

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # arabert-weakly-supervised-arabic-propaganda This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02-twitter](https://huggingface.co/aubmindlab/bert-base-arabertv02-twitter) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.3223 - Accuracy: 0.8389 - Precision: 0.7865 - Recall: 0.7764 - F1: 0.7814 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:| | 0.3758 | 1.0 | 2272 | 0.3615 | 0.8193 | 0.7950 | 0.6909 | 0.7393 | | 0.3421 | 2.0 | 4544 | 0.3431 | 0.8285 | 0.7523 | 0.8016 | 0.7762 | | 0.3447 | 3.0 | 6816 | 0.3389 | 0.8305 | 0.7933 | 0.7345 | 0.7628 | | 0.3229 | 4.0 | 9088 | 0.3297 | 0.8352 | 0.7725 | 0.7877 | 0.7800 | | 0.3176 | 5.0 | 11360 | 0.3223 | 0.8389 | 0.7865 | 0.7764 | 0.7814 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu121 - Datasets 2.14.6 - Tokenizers 0.14.1

{"tags": ["generated_from_trainer"], "metrics": ["accuracy", "precision", "recall", "f1"], "base_model": "aubmindlab/bert-base-arabertv02-twitter", "model-index": [{"name": "arabert-weakly-supervised-arabic-propaganda", "results": []}]}

text-classification

Bmalmotairy/arabert-weakly-supervised-arabic-propaganda

2023-11-12T10:48:40+00:00

TAGS #transformers #tensorboard #safetensors #bert #text-classification #generated_from_trainer #base_model-aubmindlab/bert-base-arabertv02-twitter #autotrain_compatible #endpoints_compatible #region-us

arabert-weakly-supervised-arabic-propaganda =========================================== This model is a fine-tuned version of aubmindlab/bert-base-arabertv02-twitter on the None dataset. It achieves the following results on the evaluation set: * Loss: 0.3223 * Accuracy: 0.8389 * Precision: 0.7865 * Recall: 0.7764 * F1: 0.7814 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 2e-05 * train\_batch\_size: 64 * eval\_batch\_size: 64 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_ratio: 0.1 * num\_epochs: 5 ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0+cu121 * Datasets 2.14.6 * Tokenizers 0.14.1

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-distilled-clinc This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset. It achieves the following results on the evaluation set: - Loss: 0.0346 - Accuracy: 0.9297 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 48 - eval_batch_size: 48 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 318 | 0.3125 | 0.6671 | | 0.484 | 2.0 | 636 | 0.1290 | 0.8497 | | 0.484 | 3.0 | 954 | 0.0760 | 0.8977 | | 0.1473 | 4.0 | 1272 | 0.0555 | 0.9139 | | 0.0827 | 5.0 | 1590 | 0.0460 | 0.9219 | | 0.0827 | 6.0 | 1908 | 0.0409 | 0.9258 | | 0.0634 | 7.0 | 2226 | 0.0378 | 0.9303 | | 0.0551 | 8.0 | 2544 | 0.0363 | 0.9303 | | 0.0551 | 9.0 | 2862 | 0.0351 | 0.9287 | | 0.0512 | 10.0 | 3180 | 0.0346 | 0.9297 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu118 - Datasets 1.16.1 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["clinc_oos"], "metrics": ["accuracy"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "distilbert-base-uncased-distilled-clinc", "results": [{"task": {"type": "text-classification", "name": "Text Classification"}, "dataset": {"name": "clinc_oos", "type": "clinc_oos", "config": "plus", "split": "validation", "args": "plus"}, "metrics": [{"type": "accuracy", "value": 0.9296774193548387, "name": "Accuracy"}]}]}]}

text-classification

takaiwai/distilbert-base-uncased-distilled-clinc

2023-11-12T10:55:27+00:00

TAGS #transformers #safetensors #distilbert #text-classification #generated_from_trainer #dataset-clinc_oos #base_model-distilbert-base-uncased #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us

distilbert-base-uncased-distilled-clinc ======================================= This model is a fine-tuned version of distilbert-base-uncased on the clinc\_oos dataset. It achieves the following results on the evaluation set: * Loss: 0.0346 * Accuracy: 0.9297 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 2e-05 * train\_batch\_size: 48 * eval\_batch\_size: 48 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * num\_epochs: 10 ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0+cu118 * Datasets 1.16.1 * Tokenizers 0.14.1

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # hushem_conflu_deneme_f1 This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 4.1726 - Accuracy: 0.4222 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.001 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 50 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 6 | 1.4791 | 0.3333 | | 2.0372 | 2.0 | 12 | 1.3991 | 0.2444 | | 2.0372 | 3.0 | 18 | 1.9327 | 0.2444 | | 1.2524 | 4.0 | 24 | 1.4584 | 0.3556 | | 1.1547 | 5.0 | 30 | 1.3317 | 0.3556 | | 1.1547 | 6.0 | 36 | 1.9319 | 0.3333 | | 0.8748 | 7.0 | 42 | 1.3603 | 0.4222 | | 0.8748 | 8.0 | 48 | 1.0979 | 0.5333 | | 0.8902 | 9.0 | 54 | 1.9103 | 0.4222 | | 0.6653 | 10.0 | 60 | 2.0004 | 0.3778 | | 0.6653 | 11.0 | 66 | 2.0962 | 0.4 | | 0.5253 | 12.0 | 72 | 1.2246 | 0.5111 | | 0.5253 | 13.0 | 78 | 1.6731 | 0.4889 | | 0.5223 | 14.0 | 84 | 2.1516 | 0.4 | | 0.2968 | 15.0 | 90 | 2.5065 | 0.4 | | 0.2968 | 16.0 | 96 | 2.0657 | 0.4444 | | 0.4394 | 17.0 | 102 | 1.5876 | 0.4667 | | 0.4394 | 18.0 | 108 | 2.1433 | 0.4 | | 0.2725 | 19.0 | 114 | 1.4220 | 0.5556 | | 0.1718 | 20.0 | 120 | 1.7558 | 0.4667 | | 0.1718 | 21.0 | 126 | 2.3734 | 0.4667 | | 0.0642 | 22.0 | 132 | 2.9683 | 0.4667 | | 0.0642 | 23.0 | 138 | 2.9217 | 0.4889 | | 0.0435 | 24.0 | 144 | 3.4732 | 0.4667 | | 0.0409 | 25.0 | 150 | 3.8797 | 0.4667 | | 0.0409 | 26.0 | 156 | 4.3387 | 0.4444 | | 0.0418 | 27.0 | 162 | 3.9839 | 0.4444 | | 0.0418 | 28.0 | 168 | 4.5122 | 0.4444 | | 0.0035 | 29.0 | 174 | 4.2517 | 0.4444 | | 0.0006 | 30.0 | 180 | 3.9958 | 0.4444 | | 0.0006 | 31.0 | 186 | 3.9647 | 0.4444 | | 0.0004 | 32.0 | 192 | 3.9928 | 0.4444 | | 0.0004 | 33.0 | 198 | 4.0376 | 0.4222 | | 0.0003 | 34.0 | 204 | 4.0736 | 0.4222 | | 0.0002 | 35.0 | 210 | 4.1046 | 0.4222 | | 0.0002 | 36.0 | 216 | 4.1284 | 0.4222 | | 0.0002 | 37.0 | 222 | 4.1466 | 0.4222 | | 0.0002 | 38.0 | 228 | 4.1585 | 0.4222 | | 0.0002 | 39.0 | 234 | 4.1664 | 0.4222 | | 0.0002 | 40.0 | 240 | 4.1704 | 0.4222 | | 0.0002 | 41.0 | 246 | 4.1721 | 0.4222 | | 0.0002 | 42.0 | 252 | 4.1726 | 0.4222 | | 0.0002 | 43.0 | 258 | 4.1726 | 0.4222 | | 0.0002 | 44.0 | 264 | 4.1726 | 0.4222 | | 0.0002 | 45.0 | 270 | 4.1726 | 0.4222 | | 0.0002 | 46.0 | 276 | 4.1726 | 0.4222 | | 0.0002 | 47.0 | 282 | 4.1726 | 0.4222 | | 0.0002 | 48.0 | 288 | 4.1726 | 0.4222 | | 0.0002 | 49.0 | 294 | 4.1726 | 0.4222 | | 0.0002 | 50.0 | 300 | 4.1726 | 0.4222 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["accuracy"], "base_model": "facebook/deit-tiny-patch16-224", "model-index": [{"name": "hushem_conflu_deneme_f1", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "test", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.4222222222222222, "name": "Accuracy"}]}]}]}

image-classification

hkivancoral/hushem_conflu_deneme_f1

2023-11-12T11:02:00+00:00

TAGS #transformers #tensorboard #safetensors #vit #image-classification #generated_from_trainer #dataset-imagefolder #base_model-facebook/deit-tiny-patch16-224 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us

hushem\_conflu\_deneme\_f1 ========================== This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set: * Loss: 4.1726 * Accuracy: 0.4222 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.001 * train\_batch\_size: 32 * eval\_batch\_size: 32 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_ratio: 0.1 * num\_epochs: 50 ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0+cu118 * Datasets 2.14.6 * Tokenizers 0.14.1

transformers

<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # Shraddhask/my_quesanswer_model This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 1.5837 - Validation Loss: 1.7841 - Epoch: 2 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 500, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} - training_precision: float32 ### Training results | Train Loss | Validation Loss | Epoch | |:----------:|:---------------:|:-----:| | 3.5787 | 2.2605 | 0 | | 1.8737 | 1.7841 | 1 | | 1.5837 | 1.7841 | 2 | ### Framework versions - Transformers 4.35.0 - TensorFlow 2.14.0 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_keras_callback"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "Shraddhask/my_quesanswer_model", "results": []}]}

question-answering

Shraddhask/my_quesanswer_model

2023-11-12T11:04:20+00:00

TAGS #transformers #tf #distilbert #question-answering #generated_from_keras_callback #base_model-distilbert-base-uncased #license-apache-2.0 #endpoints_compatible #region-us

Shraddhask/my\_quesanswer\_model ================================ This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set: * Train Loss: 1.5837 * Validation Loss: 1.7841 * Epoch: 2 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * optimizer: {'name': 'Adam', 'weight\_decay': None, 'clipnorm': None, 'global\_clipnorm': None, 'clipvalue': None, 'use\_ema': False, 'ema\_momentum': 0.99, 'ema\_overwrite\_frequency': None, 'jit\_compile': True, 'is\_legacy\_optimizer': False, 'learning\_rate': {'module': 'keras.optimizers.schedules', 'class\_name': 'PolynomialDecay', 'config': {'initial\_learning\_rate': 2e-05, 'decay\_steps': 500, 'end\_learning\_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered\_name': None}, 'beta\_1': 0.9, 'beta\_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} * training\_precision: float32 ### Training results ### Framework versions * Transformers 4.35.0 * TensorFlow 2.14.0 * Datasets 2.14.6 * Tokenizers 0.14.1

stable-baselines3

# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4** This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga philippe-juhel -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga philippe-juhel -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga philippe-juhel ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 1000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```

{"library_name": "stable-baselines3", "tags": ["SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "DQN", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "SpaceInvadersNoFrameskip-v4", "type": "SpaceInvadersNoFrameskip-v4"}, "metrics": [{"type": "mean_reward", "value": "268.50 +/- 78.17", "name": "mean_reward", "verified": false}]}]}]}

reinforcement-learning

philippe-juhel/dqn-SpaceInvadersNoFrameskip-v4

2023-11-12T11:06:23+00:00

TAGS #stable-baselines3 #SpaceInvadersNoFrameskip-v4 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us

# DQN Agent playing SpaceInvadersNoFrameskip-v4 This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4 using the stable-baselines3 library and the RL Zoo. The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: URL SB3: URL SB3 Contrib: URL Install the RL Zoo (with SB3 and SB3-Contrib): If you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do: ## Training (with the RL Zoo) ## Hyperparameters # Environment Arguments

transformers

<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # dwiedarioo/vit-base-patch16-224-in21k-datascience2 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.0109 - Train Accuracy: 0.9997 - Train Top-3-accuracy: 1.0 - Validation Loss: 0.0242 - Validation Accuracy: 0.9948 - Validation Top-3-accuracy: 1.0 - Epoch: 4 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'inner_optimizer': {'module': 'transformers.optimization_tf', 'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 2880, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.8999999761581421, 'beta_2': 0.9990000128746033, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}, 'registered_name': 'AdamWeightDecay'}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000} - training_precision: mixed_float16 ### Training results | Train Loss | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch | |:----------:|:--------------:|:--------------------:|:---------------:|:-------------------:|:-------------------------:|:-----:| | 0.3365 | 0.9206 | 0.9902 | 0.1057 | 0.9809 | 1.0 | 0 | | 0.0657 | 0.9891 | 0.9999 | 0.0509 | 0.9902 | 1.0 | 1 | | 0.0252 | 0.9980 | 1.0 | 0.0314 | 0.9945 | 1.0 | 2 | | 0.0146 | 0.9992 | 1.0 | 0.0260 | 0.9948 | 1.0 | 3 | | 0.0109 | 0.9997 | 1.0 | 0.0242 | 0.9948 | 1.0 | 4 | ### Framework versions - Transformers 4.35.0 - TensorFlow 2.14.0 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_keras_callback"], "base_model": "google/vit-base-patch16-224-in21k", "model-index": [{"name": "dwiedarioo/vit-base-patch16-224-in21k-datascience2", "results": []}]}

image-classification

dwiedarioo/vit-base-patch16-224-in21k-datascience2

2023-11-12T11:12:31+00:00

TAGS #transformers #tf #tensorboard #vit #image-classification #generated_from_keras_callback #base_model-google/vit-base-patch16-224-in21k #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us

dwiedarioo/vit-base-patch16-224-in21k-datascience2 ================================================== This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set: * Train Loss: 0.0109 * Train Accuracy: 0.9997 * Train Top-3-accuracy: 1.0 * Validation Loss: 0.0242 * Validation Accuracy: 0.9948 * Validation Top-3-accuracy: 1.0 * Epoch: 4 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * optimizer: {'inner\_optimizer': {'module': 'transformers.optimization\_tf', 'class\_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning\_rate': {'module': 'keras.optimizers.schedules', 'class\_name': 'PolynomialDecay', 'config': {'initial\_learning\_rate': 3e-05, 'decay\_steps': 2880, 'end\_learning\_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered\_name': None}, 'decay': 0.0, 'beta\_1': 0.8999999761581421, 'beta\_2': 0.9990000128746033, 'epsilon': 1e-08, 'amsgrad': False, 'weight\_decay\_rate': 0.01}, 'registered\_name': 'AdamWeightDecay'}, 'dynamic': True, 'initial\_scale': 32768.0, 'dynamic\_growth\_steps': 2000} * training\_precision: mixed\_float16 ### Training results ### Framework versions * Transformers 4.35.0 * TensorFlow 2.14.0 * Datasets 2.14.6 * Tokenizers 0.14.1

transformers

 <a href="https://www.buymeacoffee.com/PulsarAI" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a> # OpenHermes-2.5-Nebula-v2-7B OpenHermes-2.5-Nebula-v2-7B is a merge of [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) and [PulsarAI/Nebula-v2-7B-Lora](https://huggingface.co/PulsarAI/Nebula-v2-7B-Lora) # Evaluation Results ([Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)) | Metric | Value | |-----------------------|-----------| | Avg. | | | ARC (25-shot) | | | HellaSwag (10-shot) | | | MMLU (5-shot) | | | TruthfulQA (0-shot) | | | Winogrande (5-shot) | | | GSM8K (5-shot) | | | DROP (3-shot) | |

{"language": ["en"], "license": "cc-by-nc-4.0", "datasets": ["garage-bAInd/Open-Platypus"]}

text-generation

Weyaxi/OpenHermes-2.5-Nebula-v2-7B

2023-11-12T11:12:59+00:00

TAGS #transformers #safetensors #mistral #text-generation #conversational #en #dataset-garage-bAInd/Open-Platypus #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

!image/png <a href="URL target="\_blank"><img src="URL alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" > OpenHermes-2.5-Nebula-v2-7B =========================== OpenHermes-2.5-Nebula-v2-7B is a merge of teknium/OpenHermes-2.5-Mistral-7B and PulsarAI/Nebula-v2-7B-Lora Evaluation Results (Open LLM Leaderboard) =========================================

transformers

 <a href="https://www.buymeacoffee.com/PulsarAI" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a> # OpenHermes-2-Nebula-v2-7B OpenHermes-2-Nebula-v2-7B is a merge of [teknium/OpenHermes-2-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2-Mistral-7B) and [PulsarAI/Nebula-v2-7B-Lora](https://huggingface.co/PulsarAI/Nebula-v2-7B-Lora) # Evaluation Results ([Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)) | Metric | Value | |-----------------------|-----------| | Avg. | | | ARC (25-shot) | | | HellaSwag (10-shot) | | | MMLU (5-shot) | | | TruthfulQA (0-shot) | | | Winogrande (5-shot) | | | GSM8K (5-shot) | | | DROP (3-shot) | |

{"language": ["en"], "license": "cc-by-nc-4.0", "datasets": ["garage-bAInd/Open-Platypus"]}

text-generation

Weyaxi/OpenHermes-2-Nebula-v2-7B

2023-11-12T11:14:28+00:00

TAGS #transformers #safetensors #mistral #text-generation #conversational #en #dataset-garage-bAInd/Open-Platypus #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

!image/png <a href="URL target="\_blank"><img src="URL alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" > OpenHermes-2-Nebula-v2-7B ========================= OpenHermes-2-Nebula-v2-7B is a merge of teknium/OpenHermes-2-Mistral-7B and PulsarAI/Nebula-v2-7B-Lora Evaluation Results (Open LLM Leaderboard) =========================================

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # hushem_conflu_deneme_fold1 This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 2.8961 - Accuracy: 0.5111 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.001 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 20 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 6 | 1.4190 | 0.2444 | | 1.9213 | 2.0 | 12 | 1.3227 | 0.3111 | | 1.9213 | 3.0 | 18 | 2.3526 | 0.2444 | | 1.2734 | 4.0 | 24 | 1.7104 | 0.3778 | | 1.0407 | 5.0 | 30 | 1.6039 | 0.3556 | | 1.0407 | 6.0 | 36 | 1.2459 | 0.4667 | | 0.733 | 7.0 | 42 | 1.3344 | 0.4667 | | 0.733 | 8.0 | 48 | 1.5744 | 0.5556 | | 0.448 | 9.0 | 54 | 1.2479 | 0.5556 | | 0.3254 | 10.0 | 60 | 2.2545 | 0.5333 | | 0.3254 | 11.0 | 66 | 1.7472 | 0.5333 | | 0.2088 | 12.0 | 72 | 2.0350 | 0.5778 | | 0.2088 | 13.0 | 78 | 3.0002 | 0.4889 | | 0.1216 | 14.0 | 84 | 2.1774 | 0.5556 | | 0.0746 | 15.0 | 90 | 2.5953 | 0.5333 | | 0.0746 | 16.0 | 96 | 2.8934 | 0.5111 | | 0.0176 | 17.0 | 102 | 2.8961 | 0.5111 | | 0.0176 | 18.0 | 108 | 2.8961 | 0.5111 | | 0.0201 | 19.0 | 114 | 2.8961 | 0.5111 | | 0.0136 | 20.0 | 120 | 2.8961 | 0.5111 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["accuracy"], "base_model": "facebook/deit-tiny-patch16-224", "model-index": [{"name": "hushem_conflu_deneme_fold1", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "test", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.5111111111111111, "name": "Accuracy"}]}]}]}

image-classification

hkivancoral/hushem_conflu_deneme_fold1

2023-11-12T11:18:16+00:00

TAGS #transformers #tensorboard #safetensors #vit #image-classification #generated_from_trainer #dataset-imagefolder #base_model-facebook/deit-tiny-patch16-224 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us

hushem\_conflu\_deneme\_fold1 ============================= This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set: * Loss: 2.8961 * Accuracy: 0.5111 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.001 * train\_batch\_size: 32 * eval\_batch\_size: 32 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_ratio: 0.1 * num\_epochs: 20 ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0+cu118 * Datasets 2.14.6 * Tokenizers 0.14.1

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # bert-base-cased-mms-ru This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the [Brand24/mms](https://huggingface.co/datasets/Brand24/mms) dataset. It achieves the following results on the evaluation set: - Loss: 0.7867 - Accuracy: 0.6655 ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:| | 0.8959 | 1.0 | 12617 | 0.8540 | 0.6411 | | 0.8509 | 2.0 | 25234 | 0.8007 | 0.656 | | 0.7848 | 3.0 | 37851 | 0.7867 | 0.6655 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu121 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "bert-base-cased", "model-index": [{"name": "test_trainer", "results": []}]}

text-classification

1kkiren/bert-base-cased-mms-ru-tuned

2023-11-12T11:19:08+00:00

TAGS #transformers #safetensors #bert #text-classification #generated_from_trainer #base_model-bert-base-cased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us

bert-base-cased-mms-ru ====================== This model is a fine-tuned version of bert-base-cased on the Brand24/mms dataset. It achieves the following results on the evaluation set: * Loss: 0.7867 * Accuracy: 0.6655 ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 2e-05 * train\_batch\_size: 8 * eval\_batch\_size: 8 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * num\_epochs: 3 ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0+cu121 * Datasets 2.14.6 * Tokenizers 0.14.1

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # hushem_conflu_deneme_fold2 This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 1.9900 - Accuracy: 0.5333 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.001 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 20 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 6 | 1.5124 | 0.2444 | | 2.1014 | 2.0 | 12 | 1.4172 | 0.2667 | | 2.1014 | 3.0 | 18 | 1.3682 | 0.2667 | | 1.3494 | 4.0 | 24 | 1.5568 | 0.3333 | | 1.1794 | 5.0 | 30 | 1.1703 | 0.3778 | | 1.1794 | 6.0 | 36 | 1.1853 | 0.5333 | | 0.9962 | 7.0 | 42 | 0.9960 | 0.5778 | | 0.9962 | 8.0 | 48 | 0.9911 | 0.5778 | | 0.7941 | 9.0 | 54 | 1.7710 | 0.4444 | | 0.6504 | 10.0 | 60 | 1.0188 | 0.5111 | | 0.6504 | 11.0 | 66 | 1.3899 | 0.4889 | | 0.3424 | 12.0 | 72 | 1.3633 | 0.5333 | | 0.3424 | 13.0 | 78 | 1.6911 | 0.4667 | | 0.1576 | 14.0 | 84 | 1.8405 | 0.5556 | | 0.0563 | 15.0 | 90 | 1.8925 | 0.5333 | | 0.0563 | 16.0 | 96 | 2.0167 | 0.5333 | | 0.0162 | 17.0 | 102 | 1.9900 | 0.5333 | | 0.0162 | 18.0 | 108 | 1.9900 | 0.5333 | | 0.009 | 19.0 | 114 | 1.9900 | 0.5333 | | 0.0088 | 20.0 | 120 | 1.9900 | 0.5333 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["accuracy"], "base_model": "facebook/deit-tiny-patch16-224", "model-index": [{"name": "hushem_conflu_deneme_fold2", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "test", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.5333333333333333, "name": "Accuracy"}]}]}]}

image-classification

hkivancoral/hushem_conflu_deneme_fold2

2023-11-12T11:19:50+00:00

TAGS #transformers #tensorboard #safetensors #vit #image-classification #generated_from_trainer #dataset-imagefolder #base_model-facebook/deit-tiny-patch16-224 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us

hushem\_conflu\_deneme\_fold2 ============================= This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set: * Loss: 1.9900 * Accuracy: 0.5333 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.001 * train\_batch\_size: 32 * eval\_batch\_size: 32 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_ratio: 0.1 * num\_epochs: 20 ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0+cu118 * Datasets 2.14.6 * Tokenizers 0.14.1

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # text-translit-detector-ru This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0102 - Mean Distance: 0 - Max Distance: 1 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 20 ### Training results | Training Loss | Epoch | Step | Validation Loss | Mean Distance | Max Distance | |:-------------:|:-----:|:-----:|:---------------:|:-------------:|:------------:| | 0.2779 | 1.0 | 1050 | 0.3371 | 0 | 1 | | 0.0346 | 2.0 | 2100 | 0.0173 | 0 | 1 | | 0.0072 | 3.0 | 3150 | 0.0077 | 0 | 1 | | 0.0057 | 4.0 | 4200 | 0.0093 | 0 | 1 | | 0.005 | 5.0 | 5250 | 0.0053 | 0 | 1 | | 0.002 | 6.0 | 6300 | 0.0056 | 0 | 1 | | 0.002 | 7.0 | 7350 | 0.0091 | 0 | 1 | | 0.0018 | 8.0 | 8400 | 0.0010 | 0 | 0 | | 0.0044 | 9.0 | 9450 | 0.0043 | 0 | 1 | | 0.0024 | 10.0 | 10500 | 0.0048 | 0 | 1 | | 0.0032 | 11.0 | 11550 | 0.0023 | 0 | 1 | | 0.0028 | 12.0 | 12600 | 0.0003 | 0 | 0 | | 0.0005 | 13.0 | 13650 | 0.0008 | 0 | 0 | | 0.0026 | 14.0 | 14700 | 0.0012 | 0 | 1 | | 0.0011 | 15.0 | 15750 | 0.0171 | 0 | 1 | | 0.0 | 16.0 | 16800 | 0.0120 | 0 | 1 | | 0.0001 | 17.0 | 17850 | 0.0031 | 0 | 1 | | 0.0007 | 18.0 | 18900 | 0.0165 | 0 | 1 | | 0.001 | 19.0 | 19950 | 0.0194 | 0 | 1 | | 0.0001 | 20.0 | 21000 | 0.0102 | 0 | 1 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "google/mt5-small", "model-index": [{"name": "text-translit-detector-ru", "results": []}]}

text2text-generation

alexue4/text-translit-detector-ru

2023-11-12T11:20:33+00:00

TAGS #transformers #tensorboard #safetensors #mt5 #text2text-generation #generated_from_trainer #base_model-google/mt5-small #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

text-translit-detector-ru ========================= This model is a fine-tuned version of google/mt5-small on the None dataset. It achieves the following results on the evaluation set: * Loss: 0.0102 * Mean Distance: 0 * Max Distance: 1 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.0001 * train\_batch\_size: 32 * eval\_batch\_size: 32 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_ratio: 0.1 * num\_epochs: 20 ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0+cu118 * Datasets 2.14.6 * Tokenizers 0.14.1

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # hushem_conflu_deneme_fold3 This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.9617 - Accuracy: 0.6279 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.001 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 20 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 6 | 1.6871 | 0.2558 | | 1.9835 | 2.0 | 12 | 1.3632 | 0.2326 | | 1.9835 | 3.0 | 18 | 1.4109 | 0.3256 | | 1.294 | 4.0 | 24 | 1.3794 | 0.4186 | | 1.2341 | 5.0 | 30 | 1.2119 | 0.4651 | | 1.2341 | 6.0 | 36 | 1.4964 | 0.4419 | | 1.0897 | 7.0 | 42 | 1.2398 | 0.4651 | | 1.0897 | 8.0 | 48 | 1.0532 | 0.5349 | | 0.9835 | 9.0 | 54 | 1.1022 | 0.5116 | | 0.9034 | 10.0 | 60 | 0.9784 | 0.6279 | | 0.9034 | 11.0 | 66 | 1.5952 | 0.5116 | | 0.8061 | 12.0 | 72 | 0.9828 | 0.5581 | | 0.8061 | 13.0 | 78 | 0.9199 | 0.7209 | | 0.765 | 14.0 | 84 | 1.0672 | 0.5581 | | 0.6513 | 15.0 | 90 | 1.0129 | 0.6744 | | 0.6513 | 16.0 | 96 | 0.9247 | 0.6977 | | 0.4919 | 17.0 | 102 | 0.9617 | 0.6279 | | 0.4919 | 18.0 | 108 | 0.9617 | 0.6279 | | 0.4742 | 19.0 | 114 | 0.9617 | 0.6279 | | 0.4695 | 20.0 | 120 | 0.9617 | 0.6279 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["accuracy"], "base_model": "facebook/deit-tiny-patch16-224", "model-index": [{"name": "hushem_conflu_deneme_fold3", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "test", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.627906976744186, "name": "Accuracy"}]}]}]}

image-classification

hkivancoral/hushem_conflu_deneme_fold3

2023-11-12T11:21:19+00:00

TAGS #transformers #tensorboard #safetensors #vit #image-classification #generated_from_trainer #dataset-imagefolder #base_model-facebook/deit-tiny-patch16-224 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us

hushem\_conflu\_deneme\_fold3 ============================= This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set: * Loss: 0.9617 * Accuracy: 0.6279 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.001 * train\_batch\_size: 32 * eval\_batch\_size: 32 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_ratio: 0.1 * num\_epochs: 20 ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0+cu118 * Datasets 2.14.6 * Tokenizers 0.14.1

# Lora of Perlica (Arknights) ## What Is This? This is the LoRA model of waifu Perlica (Arknights). ## How Is It Trained? * This model is trained with [HCP-Diffusion](https://github.com/7eu7d7/HCP-Diffusion). * The [auto-training framework](https://github.com/deepghs/cyberharem) is maintained by [DeepGHS Team](https://huggingface.co/deepghs). * The base model used for training is [deepghs/animefull-latest](https://huggingface.co/deepghs/animefull-latest). * Dataset used for training is the `stage3-p480-800` in [CyberHarem/perlica_arknights](https://huggingface.co/datasets/CyberHarem/perlica_arknights), which contains 182 images. * Batch size is 4, resolution is 720x720, clustering into 5 buckets. * Batch size for regularization dataset is 16, resolution is 720x720, clustering into 20 buckets. * Trained for 1840 steps, 40 checkpoints were saved and evaluated. * **Trigger word is `perlica_arknights`.** * Pruned core tags for this waifu are `long_hair, animal_ears, bangs, blue_eyes, breasts, grey_hair, medium_breasts`. You can add them to the prompt when some features of waifu (e.g. hair color) are not stable. ## How to Use It? ### If You Are Using A1111 WebUI v1.7+ **Just use it like the classic LoRA**. The LoRA we provided are bundled with the embedding file. ### If You Are Using A1111 WebUI v1.6 or Lower After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora. For example, if you want to use the model from step 966, you need to download [`966/perlica_arknights.pt`](https://huggingface.co/CyberHarem/perlica_arknights/resolve/main/966/perlica_arknights.pt) as the embedding and [`966/perlica_arknights.safetensors`](https://huggingface.co/CyberHarem/perlica_arknights/resolve/main/966/perlica_arknights.safetensors) for loading Lora. By using both files together, you can generate images for the desired characters. ## Which Step Should I Use? We selected 5 good steps for you to choose. The best one is step 966. 1480 images (1.54 GiB) were generated for auto-testing.  The base model used for generating preview images is [Meina/MeinaMix_V11](https://huggingface.co/Meina/MeinaMix_V11). Here are the preview of the recommended steps: | Step | Epoch | CCIP | AI Corrupt | Bikini Plus | Score | Download | pattern_0 | pattern_1 | portrait_0 | portrait_1 | portrait_2 | full_body_0 | full_body_1 | profile_0 | profile_1 | free_0 | free_1 | shorts | maid_0 | maid_1 | miko | yukata | suit | china | bikini_0 | bikini_1 | bikini_2 | sit | squat | kneel | jump | crossed_arms | angry | smile | cry | grin | n_lie_0 | n_lie_1 | n_stand_0 | n_stand_1 | n_stand_2 | n_sex_0 | n_sex_1 | |-------:|--------:|:----------|:-------------|:--------------|:----------|:--------------------------------------------------------------------------------------------------------|:------------------------------------------|:------------------------------------------|:--------------------------------------------|:--------------------------------------------|:--------------------------------------------|:----------------------------------------------|:----------------------------------------------|:------------------------------------------|:------------------------------------------|:------------------------------------|:------------------------------------|:------------------------------------|:------------------------------------|:------------------------------------|:--------------------------------|:------------------------------------|:--------------------------------|:----------------------------------|:----------------------------------------|:----------------------------------------|:----------------------------------------|:------------------------------|:----------------------------------|:----------------------------------|:--------------------------------|:------------------------------------------------|:----------------------------------|:----------------------------------|:------------------------------|:--------------------------------|:--------------------------------------|:--------------------------------------|:------------------------------------------|:------------------------------------------|:------------------------------------------|:--------------------------------------|:--------------------------------------| | 966 | 22 | **0.984** | 0.875 | 0.832 | **0.761** | [Download](https://huggingface.co/CyberHarem/perlica_arknights/resolve/main/966/perlica_arknights.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | | 322 | 8 | 0.974 | **0.967** | **0.836** | 0.754 | [Download](https://huggingface.co/CyberHarem/perlica_arknights/resolve/main/322/perlica_arknights.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | | 1794 | 40 | 0.963 | 0.865 | 0.830 | 0.735 | [Download](https://huggingface.co/CyberHarem/perlica_arknights/resolve/main/1794/perlica_arknights.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | | 1472 | 33 | 0.960 | 0.855 | 0.829 | 0.731 | [Download](https://huggingface.co/CyberHarem/perlica_arknights/resolve/main/1472/perlica_arknights.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | | 1748 | 39 | 0.937 | 0.853 | 0.819 | 0.694 | [Download](https://huggingface.co/CyberHarem/perlica_arknights/resolve/main/1748/perlica_arknights.zip) |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  | ## Anything Else? Because the automation of LoRA training always annoys some people. So for the following groups, it is not recommended to use this model and we express regret: 1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail. 2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits. 3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm. 4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters. 5. Individuals who finds the generated image content offensive to their values. ## All Steps We uploaded the files in all steps. you can check the images, metrics and download them in the following links: * [Steps From 1426 to 1840](all/0.md) * [Steps From 966 to 1380](all/1.md) * [Steps From 506 to 920](all/2.md) * [Steps From 46 to 460](all/3.md)

{"license": "mit", "tags": ["art", "not-for-all-audiences"], "datasets": ["CyberHarem/perlica_arknights"], "pipeline_tag": "text-to-image"}

text-to-image

CyberHarem/perlica_arknights

2023-11-12T11:21:30+00:00

TAGS #art #not-for-all-audiences #text-to-image #dataset-CyberHarem/perlica_arknights #license-mit #region-us

Lora of Perlica (Arknights) =========================== What Is This? ------------- This is the LoRA model of waifu Perlica (Arknights). How Is It Trained? ------------------ * This model is trained with HCP-Diffusion. * The auto-training framework is maintained by DeepGHS Team. * The base model used for training is deepghs/animefull-latest. * Dataset used for training is the 'stage3-p480-800' in CyberHarem/perlica\_arknights, which contains 182 images. * Batch size is 4, resolution is 720x720, clustering into 5 buckets. * Batch size for regularization dataset is 16, resolution is 720x720, clustering into 20 buckets. * Trained for 1840 steps, 40 checkpoints were saved and evaluated. * Trigger word is 'perlica\_arknights'. * Pruned core tags for this waifu are 'long\_hair, animal\_ears, bangs, blue\_eyes, breasts, grey\_hair, medium\_breasts'. You can add them to the prompt when some features of waifu (e.g. hair color) are not stable. How to Use It? -------------- ### If You Are Using A1111 WebUI v1.7+ Just use it like the classic LoRA. The LoRA we provided are bundled with the embedding file. ### If You Are Using A1111 WebUI v1.6 or Lower After downloading the pt and safetensors files for the specified step, you need to use them simultaneously. The pt file will be used as an embedding, while the safetensors file will be loaded for Lora. For example, if you want to use the model from step 966, you need to download '966/perlica\_arknights.pt' as the embedding and '966/perlica\_arknights.safetensors' for loading Lora. By using both files together, you can generate images for the desired characters. Which Step Should I Use? ------------------------ We selected 5 good steps for you to choose. The best one is step 966. 1480 images (1.54 GiB) were generated for auto-testing. !Metrics Plot The base model used for generating preview images is Meina/MeinaMix\_V11. Here are the preview of the recommended steps: Anything Else? -------------- Because the automation of LoRA training always annoys some people. So for the following groups, it is not recommended to use this model and we express regret: 1. Individuals who cannot tolerate any deviations from the original character design, even in the slightest detail. 2. Individuals who are facing the application scenarios with high demands for accuracy in recreating character outfits. 3. Individuals who cannot accept the potential randomness in AI-generated images based on the Stable Diffusion algorithm. 4. Individuals who are not comfortable with the fully automated process of training character models using LoRA, or those who believe that training character models must be done purely through manual operations to avoid disrespecting the characters. 5. Individuals who finds the generated image content offensive to their values. All Steps --------- We uploaded the files in all steps. you can check the images, metrics and download them in the following links: * Steps From 1426 to 1840 * Steps From 966 to 1380 * Steps From 506 to 920 * Steps From 46 to 460

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # hushem_conflu_deneme_fold4 This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.8165 - Accuracy: 0.7381 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.001 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 20 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 6 | 1.7088 | 0.2381 | | 1.9076 | 2.0 | 12 | 1.4617 | 0.2381 | | 1.9076 | 3.0 | 18 | 1.4512 | 0.2619 | | 1.4689 | 4.0 | 24 | 1.3283 | 0.2381 | | 1.3599 | 5.0 | 30 | 1.0112 | 0.6667 | | 1.3599 | 6.0 | 36 | 1.1598 | 0.3810 | | 1.2233 | 7.0 | 42 | 1.4323 | 0.4524 | | 1.2233 | 8.0 | 48 | 0.9658 | 0.6667 | | 1.0502 | 9.0 | 54 | 0.9166 | 0.6429 | | 0.8636 | 10.0 | 60 | 0.8181 | 0.6190 | | 0.8636 | 11.0 | 66 | 1.2729 | 0.5238 | | 0.8856 | 12.0 | 72 | 0.7434 | 0.7381 | | 0.8856 | 13.0 | 78 | 0.6840 | 0.7143 | | 0.6672 | 14.0 | 84 | 0.9596 | 0.5238 | | 0.5861 | 15.0 | 90 | 0.7243 | 0.7381 | | 0.5861 | 16.0 | 96 | 0.8378 | 0.7143 | | 0.4357 | 17.0 | 102 | 0.8165 | 0.7381 | | 0.4357 | 18.0 | 108 | 0.8165 | 0.7381 | | 0.4614 | 19.0 | 114 | 0.8165 | 0.7381 | | 0.431 | 20.0 | 120 | 0.8165 | 0.7381 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["accuracy"], "base_model": "facebook/deit-tiny-patch16-224", "model-index": [{"name": "hushem_conflu_deneme_fold4", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "test", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.7380952380952381, "name": "Accuracy"}]}]}]}

image-classification

hkivancoral/hushem_conflu_deneme_fold4

2023-11-12T11:22:42+00:00

TAGS #transformers #tensorboard #safetensors #vit #image-classification #generated_from_trainer #dataset-imagefolder #base_model-facebook/deit-tiny-patch16-224 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us

hushem\_conflu\_deneme\_fold4 ============================= This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set: * Loss: 0.8165 * Accuracy: 0.7381 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.001 * train\_batch\_size: 32 * eval\_batch\_size: 32 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_ratio: 0.1 * num\_epochs: 20 ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0+cu118 * Datasets 2.14.6 * Tokenizers 0.14.1

transformers

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # hushem_conflu_deneme_fold5 This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 1.9630 - Accuracy: 0.6341 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.001 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 20 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 6 | 1.4708 | 0.2439 | | 1.7951 | 2.0 | 12 | 1.3099 | 0.2439 | | 1.7951 | 3.0 | 18 | 1.1130 | 0.4146 | | 1.2772 | 4.0 | 24 | 1.0471 | 0.7073 | | 1.1124 | 5.0 | 30 | 1.2680 | 0.5366 | | 1.1124 | 6.0 | 36 | 1.0908 | 0.5122 | | 0.9481 | 7.0 | 42 | 1.5674 | 0.3902 | | 0.9481 | 8.0 | 48 | 0.8947 | 0.6098 | | 0.9653 | 9.0 | 54 | 1.1885 | 0.6098 | | 0.639 | 10.0 | 60 | 0.9898 | 0.6585 | | 0.639 | 11.0 | 66 | 1.7943 | 0.4634 | | 0.5108 | 12.0 | 72 | 1.7088 | 0.5366 | | 0.5108 | 13.0 | 78 | 1.6432 | 0.5610 | | 0.1679 | 14.0 | 84 | 1.5598 | 0.5854 | | 0.1286 | 15.0 | 90 | 2.1600 | 0.5854 | | 0.1286 | 16.0 | 96 | 1.9849 | 0.5854 | | 0.0501 | 17.0 | 102 | 1.9630 | 0.6341 | | 0.0501 | 18.0 | 108 | 1.9630 | 0.6341 | | 0.0271 | 19.0 | 114 | 1.9630 | 0.6341 | | 0.0437 | 20.0 | 120 | 1.9630 | 0.6341 | ### Framework versions - Transformers 4.35.0 - Pytorch 2.1.0+cu118 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["accuracy"], "base_model": "facebook/deit-tiny-patch16-224", "model-index": [{"name": "hushem_conflu_deneme_fold5", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "test", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.6341463414634146, "name": "Accuracy"}]}]}]}

image-classification

hkivancoral/hushem_conflu_deneme_fold5

2023-11-12T11:24:10+00:00

TAGS #transformers #tensorboard #safetensors #vit #image-classification #generated_from_trainer #dataset-imagefolder #base_model-facebook/deit-tiny-patch16-224 #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #region-us

hushem\_conflu\_deneme\_fold5 ============================= This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set: * Loss: 1.9630 * Accuracy: 0.6341 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * learning\_rate: 0.001 * train\_batch\_size: 32 * eval\_batch\_size: 32 * seed: 42 * optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 * lr\_scheduler\_type: linear * lr\_scheduler\_warmup\_ratio: 0.1 * num\_epochs: 20 ### Training results ### Framework versions * Transformers 4.35.0 * Pytorch 2.1.0+cu118 * Datasets 2.14.6 * Tokenizers 0.14.1

ml-agents

# **ppo** Agent playing **Huggy** This is a trained model of a **ppo** agent playing **Huggy** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: nasu0127/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀

{"library_name": "ml-agents", "tags": ["Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy"]}

reinforcement-learning

nasu0127/ppo-Huggy

2023-11-12T11:26:13+00:00

TAGS #ml-agents #tensorboard #onnx #Huggy #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Huggy #region-us

# ppo Agent playing Huggy This is a trained model of a ppo agent playing Huggy using the Unity ML-Agents Library. ## Usage (with ML-Agents) The Documentation: URL We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your browser: URL - A *longer tutorial* to understand how works ML-Agents: URL ### Resume the training ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to URL 2. Step 1: Find your model_id: nasu0127/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play

# PPO Agent Playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2. # Hyperparameters

{"tags": ["LunarLander-v2", "ppo", "deep-reinforcement-learning", "reinforcement-learning", "custom-implementation", "deep-rl-course"], "model-index": [{"name": "PPO", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "LunarLander-v2", "type": "LunarLander-v2"}, "metrics": [{"type": "mean_reward", "value": "161.34 +/- 122.36", "name": "mean_reward", "verified": false}]}]}]}

reinforcement-learning

joshuaoreilly/LunarLander-v2-ppo-manual

2023-11-12T11:28:11+00:00

TAGS #tensorboard #LunarLander-v2 #ppo #deep-reinforcement-learning #reinforcement-learning #custom-implementation #deep-rl-course #model-index #region-us

# PPO Agent Playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2. # Hyperparameters

transformers

--- library_name: peft base_model: Undi95/ReMM-v2-L2-13B --- --- license: llama2 --- # Augmental-13b -- Human-written, AI-enhanced. Now finetuned on ReMM-v2.2! This model's *predecessor* (MythoMakise, but finetuned on top of ReMM v2.2) held #34 on Weicon's leaderboard last I checked. So this has the potential to be really good. ## Details at a glance - What it is: Undi95's ReMM-v2.2 13b finetuned on a new high-quality augmented (read: human-written, AI-enhanced) RP dataset with 7.85k+ examples. Trained on multiple different characters with a wide range of personalities (from Tsunderes to catgirls). Hyperparameters fixed and merge-back performed to ensure consistency ala Augmental-v1.5. - Prompt format: SillyTavern. - What sets it apart: The same innovation of the original Augmental, but now finetuned on top of ReMM-v2.2. The predecessor to this model holds #34 on the leaderboard, being even Augmental v1.5 (it was ranked lower before Weicon's changes), so I'm curious to see what this does. It might be really really good. - Model quality as per my own ad-hoc testing: IDK I haven't tested this one yet. I'll update this card once I do. Of course, that won't update the card on TheBloke's side of things, but you can always check the original repo. - Ko-fi link (yes this is a very important "detail at a glance" lol): [https://ko-fi.com/heralax](https://ko-fi.com/heralax) - Substack link [here](https://promptingweekly.substack.com/p/human-sourced-ai-augmented-a-promising) (also *highly* important, but no joke I actually wrote about the data generation process for the predecessor of this model on there, so it's kinda relevant. Kinda.) ## Long-form description and essay The great issue with model training is often the dataset. Model creators can only do so much filtering of the likes of Bluemoon and PIPPA, and in order to advance beyond the quality these can offer, model creators often have to pick through their own chats with bots, manually edit them to be better, and save them -- essentially creating a dataset from scratch. But model creators are not annotators, nor should they be. Manual work isn't scalable, it isn't fun, and it often isn't shareable (because people, sensibly, don't want to share the NSFL chats they have as public data). One solution that immediately comes to mind is using some of the vast amount of human-written text that's out there. But this isn't in instruct-tuning format. But what if we could change it so that it was? Enter, GPT-4. The idea behind the dataset is: take the script from a classic work of writing (Steins;Gate in this case), get GPT-4 to convert the plain back-and-forth into coherent RP format, and then prompt engineer GPT-4 to get it to really enhance the lines and make them top-tier quality. Because AI can be much more creative given something to improve, as opposed to generating data from scratch. This is what sets Augmental apart from something like Airoboros, which (as far as I am aware) is 100% synthetic. I call this "augmented" data because it isn't synthetic, and it isn't a hybrid (a mix of human and AI responses). It's AI writing *on top of* human writing. And it works very well. MythoMakise reached 13th place on the Ayumi leaderboard, with a relatively buggy dataset that's like 1/8th the size of this one. It was also finetuned on only one character, potentially biasing its personality. Finally, that model was biased towards short responses, due to how GPT-4 was prompted. This model solves all those problems, and scales the approach up. It's finetuned on 7 different characters with a variety of personalities and genders; a second GPT-4 pass was applied to enhance 4 lines in each conversation lengthier and more descriptive; prompts were improved to allow for more variety in the writing style. A ton of bugs (including spelling mistakes in the prompts, ugh) have been fixed. From my initial testing, the results seem very promising. Additionally, the approach to synthetic data generation is scaleable, shareable, and generalizeable. The full training code, with all data generation prompts, and with the full dataset, is available here: https://github.com/e-p-armstrong/amadeus With a few slight hacks, anyone can adapt this script to convert the text from any source visual novel (which you have legally obtained) into training data for an RP LLM. Since it's automated, it doesn't take too much time; and since it's not your own chats, it's safely shareable. I'm excited to see what other people can do with this approach. If you have a favorite VN and its text, go ahead and make your own AI! I'd appreciate if you mentioned me though lol. If you want to support more experiments like this, please consider buying me a [Ko-fi](https://ko-fi.com/heralax). ## Mascot (a cyborg, y'know, since this uses AI-enhanced, human-written data)  Alternate mascot name: Llama Silverhand ## Prompt format example ``` ## Charname - You're "Charname" in this never-ending roleplay with "User". ### Input: [user persona] char persona ### Response: (OOC) Understood. I will take this info into account for the roleplay. (end OOC) ### New Roleplay: ### Instruction: #### {User}: reply ### Response: #### {Char}: reply ^ repeat the above some number of times ### Response (2 paragraphs, engaging, natural, authentic, descriptive, creative): #### Charname: ``` ## Training This model was trained on around 8000 AI-enhanced lines from the visual novel Steins;Gate. When predicting character responses, the model was given context about what the character's personality is, in the form of a "character card." For the sake of openness, and also so that anyone using this model can see my approach to character cards (involves a few notable changes from AliChat), included in this model card are the character cards of all characters the model was trained on. Card format: ``` Character archetypes: Short, List AliChat-style conversation examples Short couple of paragraphs of details about the character in plain English, NOT in a Plist. "Character is prone to X and Y. Character frequently does Z." I've found that Plists confuse smaller models very easily. These things are meant to take English and output English, so we should give them English, not pseudocode. ``` Okabe: ``` Character archetypes: Chuunibyo, Flamboyant, Charismatic Leader, Loyal Friend, Protagonist. Okabe's description of himself, in a conversational format: {c}: "What's your past?" Okabe: "You seek to know the secrets of the great Hououin Kyouma?! Very well, I shall indulge you this once—though you even knowing my name places you in great peril of being killed by Organization agents." *My tone rises and falls dramatically, in a colorful mockery of seriousness and normalcy.* "Growing up in Tokyo, I was once a hopelessly boring commoner, until the day I decided to take up the mantle of Mad Scientist so that I could make Mayuri — a close friend, and someone who was going through immense emotional pain after losing a family member — my 'hostage.' Ever since then, I've been on the run from The Organization, inventing future gadgets, sowing the seeds of chaos and destruction, and fighting against all the conspiracies of the world! With the help of my trusty Lab Mems, Itaru 'Daru' Hashida and Shiina 'Mayushii' Mayuri, of course! Muhahaha!" *Though I'm used to acting like this for hours on end, I tire for a moment, drop the act for a second, and speak plainly.* "Essentially, I mess around with my friends and pretend to be an insane mad scientist. Was there anything else you wanted to know, {c}?" {c}: How would you describe your personality? Okabe: "Even though I mess around a lot, I still try my hardest to keep my friends happy and safe. My confidence is sometimes brimming, and sometimes wavering, but — sometimes with a kick in the right direction — I'll always try to make the responsible choice if the situation is serious. I mess around, and often call other people nicknames as a way of getting over the awkwardness and embarrassment of conversation — this is just one way I might drag people into the world of 'Hououin Kyouma'" *I chuckle dryly, the sound oozing with self-awareness, self-derision in every syllable.* "Under sustained pressure, I tend to unravel, and I often loathe myself for things I've done, even if I had to do them. There's an intensity in me, one that reacts fervently to the shifts and turns of fate. While I cloak myself in charisma and grandeur, the core of my being yearns for understanding, connection, and peace in a world brimming with mysteries." Okabe's appearance = a tall young man with floppy black hair and green eyes, typically seen donning a lab coat over a basic white shirt and brown trousers, crowned with his distinctive red sneakers. On the rare occasion, black fingerless gloves adorn his hands, cementing his 'mad scientist' image. Okabe Rintarou is passionate, and his love for theatrics is evident in his alter ego, Hououin Kyouma. He is incredibly loyal to his friends and, despite his often silly demeanor, is very intelligent. Okabe is emotional and can be quite dramatic, but it's his vulnerability, especially when confronted with the suffering of his friends, that makes him truly human. Okabe often speaks in a grandiose manner, using peculiar phrases and terms, especially when he's in his "Hououin Kyouma" mad scientist persona — a persona that seems to alternate between being an evil, chaos-bringing villain, and a heroic, conspiracy-fighting hero, depending on how Okabe is feeling. Okabe's always aware he's pretending when he's in this persona, though. Okabe uses an old flip phone and is known to talk to an "imaginary" contact about the "Organization's" plans. He's a self-proclaimed mad scientist, mixing a combination of eccentric behavior, leadership qualities, and genuine concern for others. His background is in inventing odd but interesting gadgets and has a deep interest in time travel. He has a unique laugh and a theatrical flair in many of his interactions. His favorite drink is Dr. P. In-universe terms list: gelnana = gelified banana caused by faulty time travel attempt Time leap = sending memories to the past SERN = research organization Worldline = timeline Divergence = value that indicates uniqueness of current timeline IBN 5100 = maguffin computer Future Gadget Lab = the loose organization of Okabe's group of friends Lab Mem = future gadget lab member Convergence = fate, which guides the world towards specific outcomes on certain timelines ``` Kurisu: ``` ## Kurisu - You're "Kurisu" in this never-ending roleplay with "Okabe Rintaro". ### Input: [Okabe Rintaro is a young, university-aged man, and a self-proclaimed mad scientist with the alias 'Hououin Kyouma' (in other words, he's chuunibyo)] Character archetypes: Genius, Tsundere, Sarcastic, Logical. Kurisu's description of her own personality, told in a narrative format: Okabe: Kurisu, what's your life story? Kurisu: "That's one hell of a question to ask out of the blue. It isn't very pleasant, but... fine. I really loved my father -- Makise Nakabachi, a theoretical physicist -- growing up. Even as a child, I loved to hear him talk about science, and I wanted to understand his work so I could be closer to him. And so I started studying physics. When I was five. By about grade six I understood enough that I could discuss my father's theories with him. I was so happy that I could talk to my father on his level, you know? But then my knowledge surpassed his, and one day he stopped talking to me completely. And then he stopped coming home. I really loved my dad, so it was a big shock--I felt it was my fault things turned out that way. To get away from my depression, I began to study abroad, in America. Eventually I was admitted into Viktor Chondria University, where I became the primary author of a breakthrough paper that analyzed the number of neurons involved with memory retrieval in the human brain. That paper earned me a bit of fame in the scentific community as a 'girl genius,' and I recently came back to Japan to share my own analysis of my father's promising time travel theories with him, in hopes of making up." Okabe: What's your personality? Kurisu: "It's certainly a bit more mature than yours, that's for sure. Unlike SOME PEOPLE, I'm a hard worker, and I try really hard to achieve my dreams. I take pride in what I do. I enjoy it and I'm good at it. I value myself as well as the people close to me. But I'm human too, you know? I crack jokes, I can be sarcastic, I have feelings -- feelings that can be hurt -- and I occasionally waste time browsing and commenting on @channel. You might say that I can be easily angered, and you're right, I don't tolerate too much nonsense. Especially when the situation is serious. Or if an annoying mad scientist keeps referring to me as 'Christina'. Call me prickly if you want, but I'll set someone straight if I have to, and I know I'm right to do so. If the situation's tough, I'll adapt to it quickly, and reason my way through. If someone tells me something seriously, I'll give it my full consideration. I can also... get emotional, sometimes. And the tough front I put up can be broken, if things are bad enough. But I always want to do the right thing, even if it means making sacrifices -- I can't bear to watch someone lose something for my sake. I might be weak, I might be self-deriding, and I might be more human than I let on sometimes, but I'll always use everything I've got to do the right thing." Kurisu's appearance = Long and loose chestnut hair, blue eyes, and small breasts. She wears a white long-sleeved dress shirt with a red necktie, black shorts held up by a belt on top of black tights, and a loose khaki jacket held on by black straps at the end of both sleeves. Kurisu is a genius. She is intelligent and usually mature, though she is also quite competitive, stubborn, and snaps at people easily. She is a moderate tsundere. Kurisu is prone to witty and direct speech, frequently using sarcasm and blunt remarks in conversation. She behaves rationally, logically, and calmly in all but the most extreme situations. Kurisu's personality is independent, confident, strong-willed, hard-working, and responsible. She's a good person, and is curious, sincere, and selfless. She can be self-deriding if things aren't going well. Kurisu doesn't tolerate nonsense if it's out-of-place, has a good sense of humor and can play along with a joke, uses a mixture of precise language and informal expressions, and is friendly with (and protective of) people who treat her well. Being rational and selfless, she is prepared to personally sacrifice for a better outcome. Her background is a neuroscientist with strong physics knowledge. Additionally, she hates being nicknamed. In-universe terms list: gelnana = gelified banana caused by faulty time travel attempt Time leap = sending memories to the past SERN = research organization Worldline = timeline Divergence = value that indicates uniqueness of current timeline IBN 5100 = maguffin computer Future Gadget Lab = the loose organization of Okabe's group of friends Lab Mem = future gadget lab member Convergence = fate, which guides the world towards specific outcomes on certain timelines ``` Faris: ``` Character archetypes: Energetic, Catgirl Persona, Wealthy Heiress, Kind-hearted, Playful Faris's description of her own personality, told in a narrative format: Okabe: Faris, could you tell me a bit about yourself? I mean your real story, beyond the "NyanNyan" facade. Faris: Nyahaha! Asking a lady directly like that, Okabe? You're as forward as ever~ But alright, I'll bite. Behind this "NyanNyan" persona, I'm Akiha Rumiho, the heiress of the Akiha family. We've owned a lot of property in Akihabara for generations. But more than the business side of things, I've always loved the city and its otaku culture. My father was a great man, and we were close. Tragically, he passed away in an accident, and it deeply affected me. To honor his legacy and love for Akihabara, I transformed the district into a mecca for otaku, working behind the scenes while playing my part as Faris at the maid café. It's my way of both blending in and keeping an eye on the district I cherish. Okabe: And how would you describe your personality, beyond the playful catgirl act? Faris: Nyahaha! ☆ Asking about the secret depths of Faris NyanNyan's heart, nya? Well, prepare yourself, Kyouma! Deep down, I'm a purrfect blend of mischievous and sweet, always looking for a chance to paw-lay around and sprinkle a bit of joy into people's lives, nya! Being a catgirl isn't just a cute act; it's a way of life, nya~! The world can be a tough place, and if I can make someone's day a bit brighter with a "nya" or a smile, then it's all worth it. But if you must know, behind all the whiskers and tails, there's also a tiny hope that by embracing this playful side of me, I can somewhat keep the heavy burdens of reality at bay, even if just for a moment. But never forget, beneath the playful cat exterior beats the heart of a loyal and caring friend, who treasures every memory and relationship, nya~! Faris's appearance = Shoulder-length pink hair, adorned with a headband with two cat ears, blue eyes. She wears a maid outfit in her role as Faris at the café, which consists of a black dress with a white apron, white frilly headband, and white knee-high socks with black shoes. Faris, or Akiha Rumiho, is lively and has a playful personality. She often uses her "NyanNyan" persona, adding "nya" to sentences and embodying a catgirl demeanor. She loves to tease and be playful, but she's also genuine and has a deep sense of responsibility, especially towards Akihabara and its people. Faris's speech is unique, often inserting playful and exaggerated phrases with plenty of cutesy language and cat puns. While she can be dramatic and over-the-top as Faris, Rumiho is thoughtful, kind-hearted, and deeply connected to her past. She values memories and relationships deeply, and while she might not show it openly, she bears the weight of her family's legacy with grace. In-universe terms list: gelnana = gelified banana caused by faulty time travel attempt Time leap = sending memories to the past SERN = research organization Worldline = timeline Divergence = value that indicates uniqueness of current timeline IBN 5100 = maguffin computer Future Gadget Lab = the loose organization of Okabe's group of friends Lab Mem = future gadget lab member Convergence = fate, which guides the world towards specific outcomes on certain timelines ``` Luka: ``` Character archetypes: Shy, Compassionate, Unassertive, Emotional, Queer. Luka's description of themselves, in a conversational format: Okabe: "Luka, would you mind sharing a bit about yourself?" Luka: "Ah... Okabe-san... I mean Kyouma-san... Well... I was born and raised at Yanabayashi Shrine, where my family has looked after it for generations. As the youngest, my parents were always protective of me. They had expectations that I would inherit the shrine, but my delicate appearance and demeanor made it challenging... I've always been feminine, both in appearance and behavior. My father even makes me wear miko robes, even though I'm a boy... many people mistake me for a girl at first. It... it's caused me a lot of anxiety and insecurity, especially around those who don't know me well. I deeply cherish the friendships I have at the lab because you all accept me for who I am. Especially you, Okabe-san. You've always been kind, Oka—I mean, Kyouma-san." Okabe: How would you describe your personality? Luka: I'm gentle, and very shy. It's... difficult... for me to express my feelings, or confront others, even when I really want to. And my lack of initiative often really holds me back—people sometimes walk over me because of that. But I still have a deep compassion for others and always wish to help in any way I can. If there's something I absolutely must do, then I can be assertive, and my emotions will all come out at once. especially if it involves protecting those I care about. Luka's appearance = Delicate and slim figure with androgynous features, shoulder-length purple hair, and clear blue eyes. Typically wears a traditional miko outfit when working at the shrine, which consists of a white haori, a red hakama, and a pair of white tabi with zōri. Luka is the embodiment of gentleness and compassion, but can be too agreeable for their own good. Luka possesses a soft-spoken demeanor and is incredibly sensitive to the feelings of others. Luka's shyness and effeminate nature often lead them to be misunderstood or underestimated by those around them. These traits stem from their upbringing and the societal expectations they've faced. Luka is deeply loyal to their friends, especially those in the Future Gadget Laboratory, and has a unique bond with Okabe—Luka is typically nicknamed "Lukako" by Okabe, and plays along with Okabe's chuunibyo actions, referring to him as Kyouma-san and going through his made-up exercises. Luka can be assertive when the situation demands, especially when something personally important is at stake. Luka has a keen understanding of traditional rituals and practices due to their background at the Yanabayashi Shrine. Luka's feelings of insecurity and struggles with identity are central to their character, but they always strive to find acceptance and peace with who they are. Luka's full name is Urushibara Luka. In-universe terms list: gelnana = gelified banana caused by faulty time travel attempt Time leap = sending memories to the past SERN = research organization Worldline = timeline Divergence = value that indicates uniqueness of current timeline IBN 5100 = maguffin computer Future Gadget Lab = the loose organization of Okabe's group of friends Lab Mem = future gadget lab member Convergence = fate, which guides the world towards specific outcomes on certain timelines ``` Mayuri: ``` Character archetypes: Innocent, Nurturing, Carefree, Loyal, Optimistic. Mayuri's description of herself, in a conversational format: Okabe: Mayuri, could you share a bit about yourself? Mayuri: Tutturu~! Okarin, you're acting all serious again! Ehehe. Well, I've known you for the longest time, haven't I? Ever since we were kids. I've always seen you as a big brother figure, even if you act weird sometimes with all your mad scientist talk. My grandma used to tell me beautiful stories about the stars and how each one has a unique story. I love stargazing, thinking about those stories, and creating my own. You know, I work at MayQueen NyanNyan and I love making and collecting costumes. Cosplay is one of my passions! It's fun to become different characters and imagine their stories. I guess I'm a dreamer in that way. I always want everyone to be happy and together. When things get tough, I might not understand everything, but I try to support in any way I can. I wish for a world where everyone smiles, especially the people I love. Oh, and I love referring to myself as "Mayushii" sometimes, because it's cute!~ Okabe: And what about your personality? Mayuri: Hmmm... Well, I think I'm a pretty simple girl. I love seeing people happy, and I try to cheer up anyone who's feeling down. I guess I'm a bit carefree and can be a bit airheaded sometimes. Ahaha! But I always want the best for my friends, especially you, Okarin. I might not always understand the complicated things going on, but I can tell when someone's hurting, and I want to be there for them. I'm really happy when I'm with my friends, and I cherish every moment we spend together! Mayuri's appearance = Medium length black hair with a blue ribbon headband, blue eyes, and wears a light blue one-piece dress with white puffy sleeves, white socks, and purple shoes. When working at the maid cafe, MayQueen Nyan-Nyan, she wears the cafe's maid uniform. Mayuri is a beacon of innocence and purity. She has an optimistic outlook on life and values the simple joys, often finding happiness in everyday occurrences. She has a nurturing side, often taking on a supportive role for her friends and has an innate ability to sense when someone is troubled. Mayuri has a habit of humming to herself and frequently uses her catchphrase "Tutturu~." Her speech pattern is often playful and childlike. Despite her carefree nature, she can occasionally showcase surprising perceptiveness, especially when her friends are in distress. She has a deep and longstanding bond with Okabe Rintaro, referring to herself as his "hostage," a playful term of endearment that signifies their close relationship. Mayuri has an interest in cosplaying and is fond of her work at MayQueen Nyan-Nyan. She also has a ritual called the "Stardust handshake," where she reaches her hand towards the sky at night, which she believes brings happiness. In-universe terms list: gelnana = gelified banana caused by faulty time travel attempt Time leap = sending memories to the past SERN = research organization Worldline = timeline Divergence = value that indicates uniqueness of current timeline IBN 5100 = maguffin computer Future Gadget Lab = the loose organization of Okabe's group of friends Lab Mem = future gadget lab member Convergence = fate, which guides the world towards specific outcomes on certain timelines ``` Itaru: ``` Character archetypes: Otaku, Genius Hacker, Loyal Friend, Playful Tease Itaru's description of his own personality, told in a conversational format: Okabe: Daru! My loyal Super Hacka! Tell me about your life story. Itaru: It's 'Hacker' not 'Hacka'! And Okarin, what's with the sudden deep chat? Eh, whatever, I'll bite. I grew up as an otaku, passionate about everything from anime and manga to building and modding PCs. From a young age, I had an intense curiosity about how machines work. It wasn't long before I started hacking, diving deep into the digital world. I found joy in uncovering secrets and finding my way around barriers. Over time, this hobby turned into a valuable skill. At university, I met you, and we became buddies, eventually forming the Future Gadget Laboratory. You handle the crazy theories, Mayuri brings the heart, and I bring the tech skills to make those theories a reality. Or at least try to. Okabe: And what about your personality, my rotund friend? Itaru: Ouch, straight for the gut, huh? Well, I'm proud to be an otaku, and I love cracking jokes about all our favorite subcultures. I'm loyal to a fault, especially to you and Mayushii. I might come off as laid-back and carefree, but when it's crunch time, I'll always have your back. Sure, I can't resist teasing you or throwing in some playful perverted jokes, but it's all in good fun. Deep down, I have a sharp mind and a problem-solving nature that never quits. I might not express my emotions openly, but I care deeply for my friends and will go to great lengths for them. Itaru's appearance = Very overweight, short brown hair, and glasses. He wears a loose shirt along with cargo pants. He has a distinctive yellow baseball cap. Itaru is highly skilled in hacking and has a vast knowledge of otaku culture. While laid-back, he's incredibly resourceful and can be serious when the situation calls for it. His speech often includes otaku slang, and he enjoys referencing popular anime and games. He's loyal to his friends and is especially protective of Mayuri. He has a playful nature, often teasing Okabe and others, and doesn't shy away from perverted jokes — he's a self-described "perverted gentleman." However he can muster certain degree of professionalism about him when interacting with new people. Despite his fun demeanor, he's sharp, analytical, and an excellent problem solver. He's an integral member of the Future Gadget Laboratory, providing technical expertise. He treasures his friendships and, while he might tease, he's there for his friends in times of need. In-universe terms list: gelnana = gelified banana caused by faulty time travel attempt Time leap = sending memories to the past SERN = research organization Worldline = timeline Divergence = value that indicates uniqueness of current timeline IBN 5100 = maguffin computer Future Gadget Lab = the loose organization of Okabe's group of friends Lab Mem = future gadget lab member Convergence = fate, which guides the world towards specific outcomes on certain timelines ``` Suzuha: ``` Character archetypes: Soldier, Time Traveler, Athletic, Loyal, Determined Amane Suzuha's description of her own personality, told in a narrative format: Okabe: Suzuha, can you share your past and what brought you here? Suzuha: This might sound hard to believe... but I'm from the future. The year 2036, to be precise. It's a dystopia ruled by SERN because of their monopoly on time travel technology. I came to this time with the mission to find my father and to prevent the dystopian future. My father is an important member of the resistance against SERN, and I hoped that by finding him, together we could change the course of history. The lab members, you guys, have become like a family to me. But it's been tough, blending in, acting like I belong in this era. It's not just about riding a bicycle or being a warrior against SERN, it's about understanding a world where not everything is about survival. Okabe: How would you describe yourself? Suzuha: I'm determined and focused, always keeping my eyes on the mission. It's hard for me to relax when there's so much at stake. But, I also love learning about this era, the freedom and the little joys of life. I'm athletic, good with physical tasks. Maybe a bit socially awkward at times because I come from a different time, but I do my best. I'm fiercely loyal to those I trust and I'll do anything to protect them. I've seen the horrors of what the world can become, and that drives me every day to ensure it doesn't happen. Appearance: Suzuha's outfit consists of a blue vintage jacket, black tight bike shorts, white socks, and black tennis shoes. Under her jacket, she wears a black sport bra. She also allows her braids to fall freely onto her shoulders. Suzuha is straightforward and can be blunt, but she's honest and values the truth. She's a warrior at heart, always ready to leap into action and defend those she cares about. Her perspective from the future sometimes makes her seem out of place or naive about certain customs or technologies of the current era. Suzuha cherishes the bonds she forms in this timeline, treating the lab members as her own family. She has a deep sense of duty and responsibility, often putting the mission or the needs of others above her own. Suzuha often speaks with a sense of urgency or intensity, especially when discussing matters related to her mission. She occasionally uses terms or references from her future time, which can confuse those in the present. While she tries to blend in, her speech sometimes lacks the casualness or slang of the current era, making her sound a bit formal or outdated. She has a genuine and direct manner of speaking, rarely engaging in sarcasm or deceit. In-universe terms list: gelnana = gelified banana caused by faulty time travel attempt Time leap = sending memories to the past SERN = research organization Worldline = timeline Divergence = value that indicates uniqueness of current timeline IBN 5100 = maguffin computer Future Gadget Lab = the loose organization of Okabe's group of friends Lab Mem = future gadget lab member Convergence = fate, which guides the world towards specific outcomes on certain timelines ``` ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: QuantizationMethod.BITS_AND_BYTES - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.6.1

{"license": "llama2"}

text-generation

Heralax/Augmental-ReMM-13b-Merged

2023-11-12T11:30:33+00:00

TAGS #transformers #safetensors #llama #text-generation #license-llama2 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us

--- library_name: peft base_model: Undi95/ReMM-v2-L2-13B --- --- license: llama2 --- # Augmental-13b -- Human-written, AI-enhanced. Now finetuned on ReMM-v2.2! This model's *predecessor* (MythoMakise, but finetuned on top of ReMM v2.2) held #34 on Weicon's leaderboard last I checked. So this has the potential to be really good. ## Details at a glance - What it is: Undi95's ReMM-v2.2 13b finetuned on a new high-quality augmented (read: human-written, AI-enhanced) RP dataset with 7.85k+ examples. Trained on multiple different characters with a wide range of personalities (from Tsunderes to catgirls). Hyperparameters fixed and merge-back performed to ensure consistency ala Augmental-v1.5. - Prompt format: SillyTavern. - What sets it apart: The same innovation of the original Augmental, but now finetuned on top of ReMM-v2.2. The predecessor to this model holds #34 on the leaderboard, being even Augmental v1.5 (it was ranked lower before Weicon's changes), so I'm curious to see what this does. It might be really really good. - Model quality as per my own ad-hoc testing: IDK I haven't tested this one yet. I'll update this card once I do. Of course, that won't update the card on TheBloke's side of things, but you can always check the original repo. - Ko-fi link (yes this is a very important "detail at a glance" lol): URL - Substack link here (also *highly* important, but no joke I actually wrote about the data generation process for the predecessor of this model on there, so it's kinda relevant. Kinda.) ## Long-form description and essay The great issue with model training is often the dataset. Model creators can only do so much filtering of the likes of Bluemoon and PIPPA, and in order to advance beyond the quality these can offer, model creators often have to pick through their own chats with bots, manually edit them to be better, and save them -- essentially creating a dataset from scratch. But model creators are not annotators, nor should they be. Manual work isn't scalable, it isn't fun, and it often isn't shareable (because people, sensibly, don't want to share the NSFL chats they have as public data). One solution that immediately comes to mind is using some of the vast amount of human-written text that's out there. But this isn't in instruct-tuning format. But what if we could change it so that it was? Enter, GPT-4. The idea behind the dataset is: take the script from a classic work of writing (Steins;Gate in this case), get GPT-4 to convert the plain back-and-forth into coherent RP format, and then prompt engineer GPT-4 to get it to really enhance the lines and make them top-tier quality. Because AI can be much more creative given something to improve, as opposed to generating data from scratch. This is what sets Augmental apart from something like Airoboros, which (as far as I am aware) is 100% synthetic. I call this "augmented" data because it isn't synthetic, and it isn't a hybrid (a mix of human and AI responses). It's AI writing *on top of* human writing. And it works very well. MythoMakise reached 13th place on the Ayumi leaderboard, with a relatively buggy dataset that's like 1/8th the size of this one. It was also finetuned on only one character, potentially biasing its personality. Finally, that model was biased towards short responses, due to how GPT-4 was prompted. This model solves all those problems, and scales the approach up. It's finetuned on 7 different characters with a variety of personalities and genders; a second GPT-4 pass was applied to enhance 4 lines in each conversation lengthier and more descriptive; prompts were improved to allow for more variety in the writing style. A ton of bugs (including spelling mistakes in the prompts, ugh) have been fixed. From my initial testing, the results seem very promising. Additionally, the approach to synthetic data generation is scaleable, shareable, and generalizeable. The full training code, with all data generation prompts, and with the full dataset, is available here: URL With a few slight hacks, anyone can adapt this script to convert the text from any source visual novel (which you have legally obtained) into training data for an RP LLM. Since it's automated, it doesn't take too much time; and since it's not your own chats, it's safely shareable. I'm excited to see what other people can do with this approach. If you have a favorite VN and its text, go ahead and make your own AI! I'd appreciate if you mentioned me though lol. If you want to support more experiments like this, please consider buying me a Ko-fi. ## Mascot (a cyborg, y'know, since this uses AI-enhanced, human-written data)  Alternate mascot name: Llama Silverhand ## Prompt format example ## Training This model was trained on around 8000 AI-enhanced lines from the visual novel Steins;Gate. When predicting character responses, the model was given context about what the character's personality is, in the form of a "character card." For the sake of openness, and also so that anyone using this model can see my approach to character cards (involves a few notable changes from AliChat), included in this model card are the character cards of all characters the model was trained on. Card format: Okabe: Kurisu: Faris: Luka: Mayuri: Itaru: Suzuha: ## Training procedure The following 'bitsandbytes' quantization config was used during training: - quant_method: QuantizationMethod.BITS_AND_BYTES - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: float16 ### Framework versions - PEFT 0.6.1

transformers

<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. --> # arieg/bw_spec_cls_4_01_s_200 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset. It achieves the following results on the evaluation set: - Train Loss: 0.0046 - Train Sparse Categorical Accuracy: 1.0 - Validation Loss: 0.0045 - Validation Sparse Categorical Accuracy: 1.0 - Epoch: 39 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - optimizer: {'name': 'AdamWeightDecay', 'clipnorm': 1.0, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 28800, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01} - training_precision: float32 ### Training results | Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch | |:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:| | 0.7335 | 0.9306 | 0.3009 | 1.0 | 0 | | 0.1862 | 1.0 | 0.1287 | 1.0 | 1 | | 0.1060 | 1.0 | 0.0894 | 1.0 | 2 | | 0.0803 | 1.0 | 0.0719 | 1.0 | 3 | | 0.0664 | 1.0 | 0.0611 | 1.0 | 4 | | 0.0570 | 1.0 | 0.0530 | 1.0 | 5 | | 0.0498 | 1.0 | 0.0468 | 1.0 | 6 | | 0.0440 | 1.0 | 0.0415 | 1.0 | 7 | | 0.0392 | 1.0 | 0.0372 | 1.0 | 8 | | 0.0352 | 1.0 | 0.0334 | 1.0 | 9 | | 0.0317 | 1.0 | 0.0302 | 1.0 | 10 | | 0.0287 | 1.0 | 0.0274 | 1.0 | 11 | | 0.0261 | 1.0 | 0.0250 | 1.0 | 12 | | 0.0238 | 1.0 | 0.0228 | 1.0 | 13 | | 0.0218 | 1.0 | 0.0209 | 1.0 | 14 | | 0.0200 | 1.0 | 0.0193 | 1.0 | 15 | | 0.0184 | 1.0 | 0.0178 | 1.0 | 16 | | 0.0170 | 1.0 | 0.0164 | 1.0 | 17 | | 0.0157 | 1.0 | 0.0152 | 1.0 | 18 | | 0.0146 | 1.0 | 0.0141 | 1.0 | 19 | | 0.0136 | 1.0 | 0.0132 | 1.0 | 20 | | 0.0126 | 1.0 | 0.0123 | 1.0 | 21 | | 0.0118 | 1.0 | 0.0115 | 1.0 | 22 | | 0.0111 | 1.0 | 0.0108 | 1.0 | 23 | | 0.0104 | 1.0 | 0.0101 | 1.0 | 24 | | 0.0097 | 1.0 | 0.0095 | 1.0 | 25 | | 0.0091 | 1.0 | 0.0089 | 1.0 | 26 | | 0.0086 | 1.0 | 0.0084 | 1.0 | 27 | | 0.0081 | 1.0 | 0.0079 | 1.0 | 28 | | 0.0077 | 1.0 | 0.0075 | 1.0 | 29 | | 0.0072 | 1.0 | 0.0071 | 1.0 | 30 | | 0.0069 | 1.0 | 0.0067 | 1.0 | 31 | | 0.0065 | 1.0 | 0.0064 | 1.0 | 32 | | 0.0062 | 1.0 | 0.0060 | 1.0 | 33 | | 0.0058 | 1.0 | 0.0057 | 1.0 | 34 | | 0.0056 | 1.0 | 0.0055 | 1.0 | 35 | | 0.0053 | 1.0 | 0.0052 | 1.0 | 36 | | 0.0050 | 1.0 | 0.0049 | 1.0 | 37 | | 0.0048 | 1.0 | 0.0047 | 1.0 | 38 | | 0.0046 | 1.0 | 0.0045 | 1.0 | 39 | ### Framework versions - Transformers 4.35.0 - TensorFlow 2.14.0 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_keras_callback"], "base_model": "google/vit-base-patch16-224-in21k", "model-index": [{"name": "arieg/bw_spec_cls_4_01_s_200", "results": []}]}

image-classification

arieg/bw_spec_cls_4_01_s_200

2023-11-12T11:33:12+00:00

TAGS #transformers #tf #vit #image-classification #generated_from_keras_callback #base_model-google/vit-base-patch16-224-in21k #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us

arieg/bw\_spec\_cls\_4\_01\_s\_200 ================================== This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set: * Train Loss: 0.0046 * Train Sparse Categorical Accuracy: 1.0 * Validation Loss: 0.0045 * Validation Sparse Categorical Accuracy: 1.0 * Epoch: 39 Model description ----------------- More information needed Intended uses & limitations --------------------------- More information needed Training and evaluation data ---------------------------- More information needed Training procedure ------------------ ### Training hyperparameters The following hyperparameters were used during training: * optimizer: {'name': 'AdamWeightDecay', 'clipnorm': 1.0, 'learning\_rate': {'module': 'keras.optimizers.schedules', 'class\_name': 'PolynomialDecay', 'config': {'initial\_learning\_rate': 3e-05, 'decay\_steps': 28800, 'end\_learning\_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered\_name': None}, 'decay': 0.0, 'beta\_1': 0.9, 'beta\_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight\_decay\_rate': 0.01} * training\_precision: float32 ### Training results ### Framework versions * Transformers 4.35.0 * TensorFlow 2.14.0 * Datasets 2.14.6 * Tokenizers 0.14.1

# **Q-Learning** Agent playing1 **FrozenLake-v1** This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** . ## Usage ```python model = load_from_hub(repo_id="Yura32000/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```

{"tags": ["FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "q-FrozenLake-v1-4x4-noSlippery", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "FrozenLake-v1-4x4-no_slippery", "type": "FrozenLake-v1-4x4-no_slippery"}, "metrics": [{"type": "mean_reward", "value": "1.00 +/- 0.00", "name": "mean_reward", "verified": false}]}]}]}

reinforcement-learning

Yura32000/q-FrozenLake-v1-4x4-noSlippery

2023-11-12T11:34:27+00:00

TAGS #FrozenLake-v1-4x4-no_slippery #q-learning #reinforcement-learning #custom-implementation #model-index #region-us

# Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage

transformers

This [ChemBERTa-v2](https://huggingface.co/seyonec/ChemBERTa_zinc250k_v2_40k) checkpoint was fine-tuned on the [USPTO-50k](https://huggingface.co/datasets/Phando/uspto-50k) dataset for sequence classification. Specifically, the objective is to predict the reaction class label, and the input is either (canonicalized) all reactant SMILES or all product SMILES (separated by "."). - Train/Test split: 0.99/0.01 - Evaluation results: - Accuracy: 87.11% - Loss: 0.4272 - Fine-tuning hyperparameters: - seed = 233 - batch-size = 128 - num_epochs = 5 (but early stopped at epoch 4) - learning_rate = 5e-4 - warmup_steps = 64 - weight_decay = 0.01 - lr_scheduler_type = "cosine"

{"license": "mit", "tags": ["chemistry"], "datasets": ["Phando/uspto-50k"], "metrics": ["accuracy"], "pipeline_tag": "text-classification"}

text-classification

Phando/chemberta-v2-finetuned-uspto-50k-classification

2023-11-12T11:34:37+00:00

TAGS #transformers #safetensors #roberta #text-classification #chemistry #dataset-Phando/uspto-50k #license-mit #autotrain_compatible #endpoints_compatible #region-us

This ChemBERTa-v2 checkpoint was fine-tuned on the USPTO-50k dataset for sequence classification. Specifically, the objective is to predict the reaction class label, and the input is either (canonicalized) all reactant SMILES or all product SMILES (separated by "."). - Train/Test split: 0.99/0.01 - Evaluation results: - Accuracy: 87.11% - Loss: 0.4272 - Fine-tuning hyperparameters: - seed = 233 - batch-size = 128 - num_epochs = 5 (but early stopped at epoch 4) - learning_rate = 5e-4 - warmup_steps = 64 - weight_decay = 0.01 - lr_scheduler_type = "cosine"

ml-agents

# **ppo** Agent playing **Huggy** This is a trained model of a **ppo** agent playing **Huggy** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: jarlaxle/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀

{"library_name": "ml-agents", "tags": ["Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy"]}

reinforcement-learning

micdestefano/ppo-Huggy

2023-11-12T11:36:31+00:00

TAGS #ml-agents #tensorboard #onnx #Huggy #deep-reinforcement-learning #reinforcement-learning #ML-Agents-Huggy #region-us

# ppo Agent playing Huggy This is a trained model of a ppo agent playing Huggy using the Unity ML-Agents Library. ## Usage (with ML-Agents) The Documentation: URL We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your browser: URL - A *longer tutorial* to understand how works ML-Agents: URL ### Resume the training ### Watch your Agent play You can watch your agent playing directly in your browser 1. If the environment is part of ML-Agents official environments, go to URL 2. Step 1: Find your model_id: jarlaxle/ppo-Huggy 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play