huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/the-beatles
+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/df75ede64ffcf049727bfbb01d323081.400x400x1.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">The Beatles</div>
+    <a href="https://genius.com/artists/the-beatles">
+    	<div style="text-align: center; font-size: 14px;">@the-beatles</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 The Beatles.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/the-beatles).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/the-beatles")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/h0p5r5wf/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 The Beatles's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3j3numex) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3j3numex/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/the-beatles')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/the-beatles")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/the-beatles")
+```
+
+## 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
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db2d69e71da261c15f87771242760b5d665f3cd57929b4e55ae317c32b104c5
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46255a18333cf38e21887ef4b8da598321d99f39e25b9411ac313092cbd9901e
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a8b57969a024e20e190b1f1ebf8da11b0ee5b5d48503133ab68ffc96d0fb4a
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce591269ee5842453fd2dfb941b08afa9dcb7fca36bb49b0a4b1fe61941c6e86
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6bca18872f98ea1f3067aeed2ea8466e4f17513f6b052e942280bbb7b375238
+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 +1,190 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 145,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013679786386078908,
+      "loss": 3.2135,
+      "step": 5
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00013559617012171195,
+      "loss": 3.0835,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00013360900754314024,
+      "loss": 3.0207,
+      "step": 15
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00013085967378942767,
+      "loss": 2.9809,
+      "step": 20
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001273804022850966,
+      "loss": 3.0379,
+      "step": 25
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00012321198430740717,
+      "loss": 2.7644,
+      "step": 30
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00011840329074592678,
+      "loss": 2.8189,
+      "step": 35
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00011301069913603339,
+      "loss": 2.6556,
+      "step": 40
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00010709743268385944,
+      "loss": 2.9363,
+      "step": 45
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00010073281903200561,
+      "loss": 2.5794,
+      "step": 50
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.399147745631814e-05,
+      "loss": 2.4779,
+      "step": 55
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.695244402310457e-05,
+      "loss": 2.9374,
+      "step": 60
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 7.969824496351968e-05,
+      "loss": 2.6178,
+      "step": 65
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.231392912895965e-05,
+      "loss": 2.7956,
+      "step": 70
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 6.488607087104036e-05,
+      "loss": 2.7369,
+      "step": 75
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 5.750175503648034e-05,
+      "loss": 2.8983,
+      "step": 80
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 5.0247555976895465e-05,
+      "loss": 2.6613,
+      "step": 85
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.320852254368187e-05,
+      "loss": 2.8101,
+      "step": 90
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.64671809679944e-05,
+      "loss": 2.7433,
+      "step": 95
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.0102567316140575e-05,
+      "loss": 2.6317,
+      "step": 100
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.418930086396663e-05,
+      "loss": 2.8128,
+      "step": 105
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.879670925407324e-05,
+      "loss": 2.4389,
+      "step": 110
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3988015692592839e-05,
+      "loss": 2.6243,
+      "step": 115
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.819597714903392e-06,
+      "loss": 2.6688,
+      "step": 120
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.340326210572357e-06,
+      "loss": 2.5304,
+      "step": 125
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.590992456859759e-06,
+      "loss": 2.6001,
+      "step": 130
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.6038298782880553e-06,
+      "loss": 2.5575,
+      "step": 135
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.0213613921093164e-07,
+      "loss": 2.6308,
+      "step": 140
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 2.8741,
+      "step": 145
+    }
+  ],
+  "max_steps": 145,
+  "num_train_epochs": 1,
+  "total_flos": 150765502464000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a31bc268644de6146180d3e698e67bd8d1d36627678947674421707172860117
+size 2671