Upload README.md

README.md

@@ -0,0 +1,473 @@
+---
+base_model: LLM360/AmberChat
+datasets:
+- WizardLM/WizardLM_evol_instruct_V2_196k
+- icybee/share_gpt_90k_v1
+inference: false
+language:
+- en
+library_name: transformers
+license: apache-2.0
+model_creator: LLM360
+model_name: AmberChat
+model_type: amber
+pipeline_tag: text-generation
+prompt_template: 'A chat between a curious user and an artificial intelligence assistant.
+  The assistant gives helpful, detailed, and polite answers to the user''s questions.
+  USER: {prompt} ASSISTANT:
+
+  '
+quantized_by: TheBloke
+tags:
+- nlp
+- llm
+widget:
+- example_title: example 1
+  output:
+    text: "Mounting a TV to drywall safely is crucial to ensure the longevity of your\
+      \ TV and the wall. Here's a step-by-step guide on how to do it safely:\n 1.\
+      \ Choose the right mount: Choose a mount that is compatible with your TV and\
+      \ the wall. Make sure the mount is rated for drywall and not just wood or concrete.\n\
+      \ 2. Prepare the wall: Before mounting the TV, make sure the wall is clean and\
+      \ free from any debris or paint. Use a stud finder to locate the studs in the\
+      \ wall.\n 3. Install the mount: Follow the manufacturer's instructions for mounting\
+      \ the TV to the wall. Use appropriate hardware and tools to secure the mount\
+      \ to the wall.\n 4. Level the TV: Level the TV on the mount using a spirit level\
+      \ or a leveling kit provided by the mount manufacturer.\n 5. Attach the TV to\
+      \ the mount: Attach the TV to the mount using the appropriate hardware and tools.\
+      \ Tighten the bolts and screws to ensure the TV is securely attached.\n 6. Connect\
+      \ the cables: Connect the TV cables to the appropriate ports on the back of\
+      \ the TV and the mount.\n 7. Test the mount: Test the mount to ensure it's secure\
+      \ and stable. Adjust the mount as needed to ensure the TV is level and secure.\n\
+      \ Mounting a TV to drywall safely is crucial to avoid damaging the wall or the\
+      \ TV. Follow these steps carefully and use appropriate tools and hardware to\
+      \ ensure a secure and stable installation."
+  text: How do I mount a tv to drywall safely?
+- example_title: example 2
+  output:
+    text: The adjective that can be used to describe the opposite of calm is "anxious"
+      or "stressed." So, from happy to sad, we can say that happy is to sad as calm
+      is to anxious or stressed.
+  text: Happy is to sad as calm is to _.
+---
+<!-- markdownlint-disable MD041 -->
+
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<div style="display: flex; justify-content: space-between; width: 100%;">
+    <div style="display: flex; flex-direction: column; align-items: flex-start;">
+        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
+    </div>
+    <div style="display: flex; flex-direction: column; align-items: flex-end;">
+        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
+    </div>
+</div>
+<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
+<!-- header end -->
+
+# AmberChat - AWQ
+- Model creator: [LLM360](https://huggingface.co/LLM360)
+- Original model: [AmberChat](https://huggingface.co/LLM360/AmberChat)
+
+<!-- description start -->
+## Description
+
+This repo contains AWQ model files for [LLM360's AmberChat](https://huggingface.co/LLM360/AmberChat).
+
+These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
+
+
+### About AWQ
+
+AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
+
+AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
+
+It is supported by:
+
+- [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
+- [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types.
+- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
+- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
+- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
+
+<!-- description end -->
+<!-- repositories-available start -->
+## Repositories available
+
+* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/AmberChat-AWQ)
+* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/AmberChat-GPTQ)
+* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/AmberChat-GGUF)
+* [LLM360's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/LLM360/AmberChat)
+<!-- repositories-available end -->
+
+<!-- prompt-template start -->
+## Prompt template: Vicuna
+
+```
+A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
+
+```
+
+<!-- prompt-template end -->
+
+
+<!-- README_AWQ.md-provided-files start -->
+## Provided files, and AWQ parameters
+
+I currently release 128g GEMM models only. The addition of group_size 32 models, and GEMV kernel models, is being actively considered.
+
+Models are released as sharded safetensors files.
+
+| Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
+| ------ | ---- | -- | ----------- | ------- | ---- |
+| [main](https://huggingface.co/TheBloke/AmberChat-AWQ/tree/main) | 4 | 128 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 2048 | 3.89 GB
+
+<!-- README_AWQ.md-provided-files end -->
+
+<!-- README_AWQ.md-text-generation-webui start -->
+## How to easily download and use this model in [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
+
+Please make sure you're using the latest version of [text-generation-webui](https://github.com/oobabooga/text-generation-webui).
+
+It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
+
+1. Click the **Model tab**.
+2. Under **Download custom model or LoRA**, enter `TheBloke/AmberChat-AWQ`.
+3. Click **Download**.
+4. The model will start downloading. Once it's finished it will say "Done".
+5. In the top left, click the refresh icon next to **Model**.
+6. In the **Model** dropdown, choose the model you just downloaded: `AmberChat-AWQ`
+7. Select **Loader: AutoAWQ**.
+8. Click Load, and the model will load and is now ready for use.
+9. If you want any custom settings, set them and then click **Save settings for this model** followed by **Reload the Model** in the top right.
+10. Once you're ready, click the **Text Generation** tab and enter a prompt to get started!
+<!-- README_AWQ.md-text-generation-webui end -->
+
+<!-- README_AWQ.md-use-from-vllm start -->
+## Multi-user inference server: vLLM
+
+Documentation on installing and using vLLM [can be found here](https://vllm.readthedocs.io/en/latest/).
+
+- Please ensure you are using vLLM version 0.2 or later.
+- When using vLLM as a server, pass the `--quantization awq` parameter.
+
+For example:
+
+```shell
+python3 -m vllm.entrypoints.api_server --model TheBloke/AmberChat-AWQ --quantization awq --dtype auto
+```
+
+- When using vLLM from Python code, again set `quantization=awq`.
+
+For example:
+
+```python
+from vllm import LLM, SamplingParams
+
+prompts = [
+    "Tell me about AI",
+    "Write a story about llamas",
+    "What is 291 - 150?",
+    "How much wood would a woodchuck chuck if a woodchuck could chuck wood?",
+]
+prompt_template=f'''A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
+'''
+
+prompts = [prompt_template.format(prompt=prompt) for prompt in prompts]
+
+sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
+
+llm = LLM(model="TheBloke/AmberChat-AWQ", quantization="awq", dtype="auto")
+
+outputs = llm.generate(prompts, sampling_params)
+
+# Print the outputs.
+for output in outputs:
+    prompt = output.prompt
+    generated_text = output.outputs[0].text
+    print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+```
+<!-- README_AWQ.md-use-from-vllm start -->
+
+<!-- README_AWQ.md-use-from-tgi start -->
+## Multi-user inference server: Hugging Face Text Generation Inference (TGI)
+
+Use TGI version 1.1.0 or later. The official Docker container is: `ghcr.io/huggingface/text-generation-inference:1.1.0`
+
+Example Docker parameters:
+
+```shell
+--model-id TheBloke/AmberChat-AWQ --port 3000 --quantize awq --max-input-length 3696 --max-total-tokens 4096 --max-batch-prefill-tokens 4096
+```
+
+Example Python code for interfacing with TGI (requires [huggingface-hub](https://github.com/huggingface/huggingface_hub) 0.17.0 or later):
+
+```shell
+pip3 install huggingface-hub
+```
+
+```python
+from huggingface_hub import InferenceClient
+
+endpoint_url = "https://your-endpoint-url-here"
+
+prompt = "Tell me about AI"
+prompt_template=f'''A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
+'''
+
+client = InferenceClient(endpoint_url)
+response = client.text_generation(prompt,
+                                  max_new_tokens=128,
+                                  do_sample=True,
+                                  temperature=0.7,
+                                  top_p=0.95,
+                                  top_k=40,
+                                  repetition_penalty=1.1)
+
+print(f"Model output: ", response)
+```
+<!-- README_AWQ.md-use-from-tgi end -->
+
+<!-- README_AWQ.md-use-from-python start -->
+## Inference from Python code using Transformers
+
+### Install the necessary packages
+
+- Requires: [Transformers](https://huggingface.co/docs/transformers) 4.35.0 or later.
+- Requires: [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) 0.1.6 or later.
+
+```shell
+pip3 install --upgrade "autoawq>=0.1.6" "transformers>=4.35.0"
+```
+
+Note that if you are using PyTorch 2.0.1, the above AutoAWQ command will automatically upgrade you to PyTorch 2.1.0.
+
+If you are using CUDA 11.8 and wish to continue using PyTorch 2.0.1, instead run this command:
+
+```shell
+pip3 install https://github.com/casper-hansen/AutoAWQ/releases/download/v0.1.6/autoawq-0.1.6+cu118-cp310-cp310-linux_x86_64.whl
+```
+
+If you have problems installing [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) using the pre-built wheels, install it from source instead:
+
+```shell
+pip3 uninstall -y autoawq
+git clone https://github.com/casper-hansen/AutoAWQ
+cd AutoAWQ
+pip3 install .
+```
+
+### Transformers example code (requires Transformers 4.35.0 and later)
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+
+model_name_or_path = "TheBloke/AmberChat-AWQ"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name_or_path,
+    low_cpu_mem_usage=True,
+    device_map="cuda:0"
+)
+
+# Using the text streamer to stream output one token at a time
+streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+
+prompt = "Tell me about AI"
+prompt_template=f'''A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:
+'''
+
+# Convert prompt to tokens
+tokens = tokenizer(
+    prompt_template,
+    return_tensors='pt'
+).input_ids.cuda()
+
+generation_params = {
+    "do_sample": True,
+    "temperature": 0.7,
+    "top_p": 0.95,
+    "top_k": 40,
+    "max_new_tokens": 512,
+    "repetition_penalty": 1.1
+}
+
+# Generate streamed output, visible one token at a time
+generation_output = model.generate(
+    tokens,
+    streamer=streamer,
+    **generation_params
+)
+
+# Generation without a streamer, which will include the prompt in the output
+generation_output = model.generate(
+    tokens,
+    **generation_params
+)
+
+# Get the tokens from the output, decode them, print them
+token_output = generation_output[0]
+text_output = tokenizer.decode(token_output)
+print("model.generate output: ", text_output)
+
+# Inference is also possible via Transformers' pipeline
+from transformers import pipeline
+
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    **generation_params
+)
+
+pipe_output = pipe(prompt_template)[0]['generated_text']
+print("pipeline output: ", pipe_output)
+
+```
+<!-- README_AWQ.md-use-from-python end -->
+
+<!-- README_AWQ.md-compatibility start -->
+## Compatibility
+
+The files provided are tested to work with:
+
+- [text-generation-webui](https://github.com/oobabooga/text-generation-webui) using `Loader: AutoAWQ`.
+- [vLLM](https://github.com/vllm-project/vllm) version 0.2.0 and later.
+- [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) version 1.1.0 and later.
+- [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later.
+- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) version 0.1.1 and later.
+
+<!-- README_AWQ.md-compatibility end -->
+
+<!-- footer start -->
+<!-- 200823 -->
+## Discord
+
+For further support, and discussions on these models and AI in general, join us at:
+
+[TheBloke AI's Discord server](https://discord.gg/theblokeai)
+
+## Thanks, and how to contribute
+
+Thanks to the [chirper.ai](https://chirper.ai) team!
+
+Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
+
+I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
+
+If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
+
+Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
+
+* Patreon: https://patreon.com/TheBlokeAI
+* Ko-Fi: https://ko-fi.com/TheBlokeAI
+
+**Special thanks to**: Aemon Algiz.
+
+**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
+
+
+Thank you to all my generous patrons and donaters!
+
+And thank you again to a16z for their generous grant.
+
+<!-- footer end -->
+
+# Original model card: LLM360's AmberChat
+
+# AmberChat
+
+
+We present AmberChat, an instruction following model finetuned from [LLM360/Amber](https://huggingface.co/LLM360/Amber).
+
+## Model Description
+
+- **Model type:** Language model with the same architecture as LLaMA-7B
+- **Language(s) (NLP):** English
+- **License:** Apache 2.0
+- **Resources for more information:**
+  - [Metrics](https://github.com/LLM360/Analysis360)
+  - [Fully processed Amber pretraining data](https://huggingface.co/datasets/LLM360/AmberDatasets)
+
+
+# Loading AmberChat 
+
+```python
+import torch
+from transformers import LlamaTokenizer, LlamaForCausalLM
+
+tokenizer = LlamaTokenizer.from_pretrained("LLM360/AmberChat")
+model = LlamaForCausalLM.from_pretrained("LLM360/AmberChat")
+
+#template adapated from fastchat
+template= "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.\n### Human: Got any creative ideas for a 10 year old’s birthday?\n### Assistant: Of course! Here are some creative ideas for a 10-year-old's birthday party:\n1. Treasure Hunt: Organize a treasure hunt in your backyard or nearby park. Create clues and riddles for the kids to solve, leading them to hidden treasures and surprises.\n2. Science Party: Plan a science-themed party where kids can engage in fun and interactive experiments. You can set up different stations with activities like making slime, erupting volcanoes, or creating simple chemical reactions.\n3. Outdoor Movie Night: Set up a backyard movie night with a projector and a large screen or white sheet. Create a cozy seating area with blankets and pillows, and serve popcorn and snacks while the kids enjoy a favorite movie under the stars.\n4. DIY Crafts Party: Arrange a craft party where kids can unleash their creativity. Provide a variety of craft supplies like beads, paints, and fabrics, and let them create their own unique masterpieces to take home as party favors.\n5. Sports Olympics: Host a mini Olympics event with various sports and games. Set up different stations for activities like sack races, relay races, basketball shooting, and obstacle courses. Give out medals or certificates to the participants.\n6. Cooking Party: Have a cooking-themed party where the kids can prepare their own mini pizzas, cupcakes, or cookies. Provide toppings, frosting, and decorating supplies, and let them get hands-on in the kitchen.\n7. Superhero Training Camp: Create a superhero-themed party where the kids can engage in fun training activities. Set up an obstacle course, have them design their own superhero capes or masks, and organize superhero-themed games and challenges.\n8. Outdoor Adventure: Plan an outdoor adventure party at a local park or nature reserve. Arrange activities like hiking, nature scavenger hunts, or a picnic with games. Encourage exploration and appreciation for the outdoors.\nRemember to tailor the activities to the birthday child's interests and preferences. Have a great celebration!\n### Human: {prompt}\n### Assistant:"
+
+prompt = "How do I mount a tv to drywall safely?"
+
+input_str = template.format(prompt=prompt)
+input_ids = tokenizer(input_str, return_tensors="pt").input_ids
+outputs = model.generate(input_ids, max_length=1000)
+print(tokenizer.batch_decode(outputs[:, input_ids.shape[1]:-1])[0].strip())
+```
+
+Alternatively, you may use [FastChat](https://github.com/lm-sys/FastChat):
+```bash
+python3 -m fastchat.serve.cli --model-path LLM360/AmberChat
+```
+
+# AmberChat Finetuning Details
+
+## DataMix
+| Subset      | Number of rows |  License   |
+| ----------- | ----------- | ----------- |
+| WizardLM/WizardLM_evol_instruct_V2_196k      | 143k       |  |
+| icybee/share_gpt_90k_v1   | 90k        | cc0-1.0 |
+| Total | 233k |  |
+
+## Hyperparameters
+| Hyperparameter      | Value |
+| ----------- | ----------- |
+| Total Parameters      | 6.7B       |
+| Hidden Size   | 4096        |
+| Intermediate Size (MLPs)   | 11008        |
+| Number of Attention Heads   | 32        |
+| Number of Hidden Lyaers  | 32        |
+| RMSNorm ɛ  | 1e^-6        |
+| Max Seq Length   | 2048        |
+| Vocab Size | 32000 |
+
+| Training Hyperparameter      | Value |
+| ----------- | ----------- |
+| learning_rate      | 2e-5       |
+| num_train_epochs  |  3        |
+| per_device_train_batch_size   | 2        |
+| gradient_accumulation_steps  | 16        |
+| warmup_ratio | 0.04      |
+| model_max_length | 2048     |
+
+
+# Evaluation
+
+| Model                                                | MT-Bench                                                  | 
+|------------------------------------------------------|------------------------------------------------------------|
+| LLM360/Amber 359 | 2.48750 | 
+| **LLM360/AmberChat** | **5.428125** |
+
+# Citation
+
+**BibTeX:**
+
+```bibtex
+@article{xxx,
+  title={XXX},
+  author={XXX},
+  journal={XXX},
+  year={2023}
+}
+```