huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/big-baby-tape
+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/d3fc4853f74c35383ec68670bbd292eb.709x709x1.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">Big Baby Tape</div>
+    <a href="https://genius.com/artists/big-baby-tape">
+    	<div style="text-align: center; font-size: 14px;">@big-baby-tape</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 Big Baby Tape.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/big-baby-tape).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/big-baby-tape")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1htarx7k/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 Big Baby Tape's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3g1oe5ka) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3g1oe5ka/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/big-baby-tape')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/big-baby-tape")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/big-baby-tape")
+```
+
+## 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": "4.10.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 1.8946211338043213, "eval_runtime": 10.5235, "eval_samples_per_second": 22.141, "eval_steps_per_second": 2.851, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44d87f70a283f33a59661b0fe30fe1f9cff19d9800e930e3708095a5e6458c56
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5840e665a12f250aefcbd09f8ad23143611ffa62d50914515f5b3acf3bd54c9d
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b476da6a207efc2b6a2780dae8d0dc6d3f8797b977d1cbb20db331183108af2
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911921c48e2767fcdd364e55b8ac5adb7fa66719512f66f920a291ef0ff95179
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00dd6b6c01d14ec8bb955c14a18bd11e818291c6d3cf3ac44048cedcc0186d76
+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 +1,174 @@
+{
+  "best_metric": 1.8946211338043213,
+  "best_model_checkpoint": "output/big-baby-tape/checkpoint-126",
+  "epoch": 1.0,
+  "global_step": 126,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0001366676095727718,
+      "loss": 2.7486,
+      "step": 5
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00013507870183531476,
+      "loss": 2.6211,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001324579391569924,
+      "loss": 2.2625,
+      "step": 15
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00012884599993319768,
+      "loss": 2.3757,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00012429894719210777,
+      "loss": 2.3396,
+      "step": 25
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00011888735840752609,
+      "loss": 2.2627,
+      "step": 30
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00011269523002449659,
+      "loss": 2.226,
+      "step": 35
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001058186737011911,
+      "loss": 2.1916,
+      "step": 40
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.836442450346448e-05,
+      "loss": 2.2987,
+      "step": 45
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.044818420726556e-05,
+      "loss": 2.0771,
+      "step": 50
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.219282542347867e-05,
+      "loss": 2.1651,
+      "step": 55
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.372648442002871e-05,
+      "loss": 2.1705,
+      "step": 60
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 6.518057224367617e-05,
+      "loss": 2.0684,
+      "step": 65
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5.668773501204858e-05,
+      "loss": 2.025,
+      "step": 70
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.837979503541197e-05,
+      "loss": 2.1328,
+      "step": 75
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.0385704725240065e-05,
+      "loss": 2.076,
+      "step": 80
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.282954504816644e-05,
+      "loss": 2.0965,
+      "step": 85
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.5828599592490882e-05,
+      "loss": 2.157,
+      "step": 90
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.9491534140783314e-05,
+      "loss": 2.0402,
+      "step": 95
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3916710004507539e-05,
+      "loss": 2.0006,
+      "step": 100
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.190657300387505e-06,
+      "loss": 1.993,
+      "step": 105
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5.38673186569003e-06,
+      "loss": 2.0394,
+      "step": 110
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.5639766592291746e-06,
+      "loss": 1.9176,
+      "step": 115
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.662053209561833e-07,
+      "loss": 2.0078,
+      "step": 120
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.132211474400556e-08,
+      "loss": 2.0426,
+      "step": 125
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.8946211338043213,
+      "eval_runtime": 10.3833,
+      "eval_samples_per_second": 22.44,
+      "eval_steps_per_second": 2.889,
+      "step": 126
+    }
+  ],
+  "max_steps": 126,
+  "num_train_epochs": 1,
+  "total_flos": 130776662016000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a697d9fe12925fe593db615b6532711275101c30a75091651a57d54878a90dd9
+size 2671