huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/bill-wurtz
+tags:
+- huggingartists
+- lyrics
+- lm-head
+- causal-lm
+widget:
+- text: "I am"
+---
+
+<div class="inline-flex flex-col" style="line-height: 1.5;">
+    <div class="flex">
+        <div
+			style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/0d4b35ed37091d5f6fd59806810e14ca.1000x1000x1.jpg&#39;)">
+        </div>
+    </div>
+    <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
+    <div style="text-align: center; font-size: 16px; font-weight: 800">Bill Wurtz</div>
+    <a href="https://genius.com/artists/bill-wurtz">
+    	<div style="text-align: center; font-size: 14px;">@bill-wurtz</div>
+    </a>
+</div>
+
+I was made with [huggingartists](https://github.com/AlekseyKorshuk/huggingartists).
+
+Create your own bot based on your favorite artist with [the demo](https://colab.research.google.com/github/AlekseyKorshuk/huggingartists/blob/master/huggingartists-demo.ipynb)!
+
+## How does it work?
+
+To understand how the model was developed, check the [W&B report](https://wandb.ai/huggingartists/huggingartists/reportlist).
+
+## Training data
+
+The model was trained on lyrics from Bill Wurtz.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/bill-wurtz).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/bill-wurtz")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3m596wb1/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
+
+## Training procedure
+
+The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Bill Wurtz's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/tn25vkjp) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/tn25vkjp/artifacts) is logged and versioned.
+
+## How to use
+
+You can use this model directly with a pipeline for text generation:
+
+```python
+from transformers import pipeline
+generator = pipeline('text-generation',
+                     model='huggingartists/bill-wurtz')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/bill-wurtz")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/bill-wurtz")
+```
+
+## Limitations and bias
+
+The model suffers from [the same limitations and bias as GPT-2](https://huggingface.co/gpt2#limitations-and-bias).
+
+In addition, the data present in the user's tweets further affects the text generated by the model.
+
+## About
+
+*Built by Aleksey Korshuk*
+
+[![Follow](https://img.shields.io/github/followers/AlekseyKorshuk?style=social)](https://github.com/AlekseyKorshuk)
+
+[![Follow](https://img.shields.io/twitter/follow/alekseykorshuk?style=social)](https://twitter.com/intent/follow?screen_name=alekseykorshuk)
+
+[![Follow](https://img.shields.io/badge/dynamic/json?color=blue&label=Telegram%20Channel&query=%24.result&url=https%3A%2F%2Fapi.telegram.org%2Fbot1929545866%3AAAFGhV-KKnegEcLiyYJxsc4zV6C-bdPEBtQ%2FgetChatMemberCount%3Fchat_id%3D-1001253621662&style=social&logo=telegram)](https://t.me/joinchat/_CQ04KjcJ-4yZTky)
+
+For more details, visit the project repository.
+
+[![GitHub stars](https://img.shields.io/github/stars/AlekseyKorshuk/huggingartists?style=social)](https://github.com/AlekseyKorshuk/huggingartists)

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 200,
+      "min_length": 100,
+      "temperature": 1.0,
+      "top_p": 0.95
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 3.056016445159912, "eval_runtime": 0.7021, "eval_samples_per_second": 38.458, "eval_steps_per_second": 5.698, "epoch": 5.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5eea9a74d99aea650690be8e5916b60d87d02d8e31dc45b59fa4bd1904a4b58
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a38c311db28275ebd22bd1a96b5f1ae0705768584e0b02b91c6d3f51f16d1a
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63382be8feee6fe2b303cf897efe67e158593589b9171b749dab61667b6c81f2
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1232337b23975f069a764f8e344e5636ceb4c40315428483d2aca49f6796a108
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d0d89fe51412bc7eecc43912be03d94b03466976a036bba499f0a41644d0f8
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -0,0 +1,92 @@
+{
+  "best_metric": 3.056016445159912,
+  "best_model_checkpoint": "output/bill-wurtz/checkpoint-54",
+  "epoch": 2.0,
+  "global_step": 54,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00012591446386292745,
+      "loss": 3.5789,
+      "step": 5
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.577107195028616e-05,
+      "loss": 3.3728,
+      "step": 10
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5.668773501204858e-05,
+      "loss": 3.2429,
+      "step": 15
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.152382364220488e-05,
+      "loss": 3.2491,
+      "step": 20
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.849121878224087e-06,
+      "loss": 3.1415,
+      "step": 25
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.1433706283569336,
+      "eval_runtime": 0.6351,
+      "eval_samples_per_second": 42.515,
+      "eval_steps_per_second": 6.299,
+      "step": 27
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 4.137086214086682e-06,
+      "loss": 2.9586,
+      "step": 30
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2.7634920609188867e-05,
+      "loss": 3.0624,
+      "step": 35
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 6.461126473674133e-05,
+      "loss": 2.9663,
+      "step": 40
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00010290000000000001,
+      "loss": 2.8978,
+      "step": 45
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.0001299031991261861,
+      "loss": 2.9441,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.056016445159912,
+      "eval_runtime": 0.6316,
+      "eval_samples_per_second": 42.746,
+      "eval_steps_per_second": 6.333,
+      "step": 54
+    }
+  ],
+  "max_steps": 135,
+  "num_train_epochs": 5,
+  "total_flos": 56439078912000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74110011f543625430a4ba42009eb3a204c303837c8ad074906c1a42d538d532
+size 2671