huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/bob-dylan
+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/22306423b6ad8777d1ed5b33ad8b0d0b.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">Bob Dylan</div>
+    <a href="https://genius.com/artists/bob-dylan">
+    	<div style="text-align: center; font-size: 14px;">@bob-dylan</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 Bob Dylan.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/bob-dylan).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/bob-dylan")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1um93nq1/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 Bob Dylan's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2houqbly) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2houqbly/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/bob-dylan')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/bob-dylan")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/bob-dylan")
+```
+
+## 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 +1,42 @@
+{
+  "_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,
+  "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,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "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": "4.12.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 2.670438766479492, "eval_runtime": 18.7517, "eval_samples_per_second": 22.665, "eval_steps_per_second": 2.88, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab78a956832fea0e65d8e04d7f51135871ced4607d5d7b2674d7c0c12e70558
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d791f4654e6ea4e0717077e3594974eb5b7059da8528fddd6f83eb69e9b560e4
+size 995604017

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aee67697cc2e4e18a857a1d535e3c39d413deafb0e0f528766a14c88acec422
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d0cdbe9de079b14ddbb06d046ee4472dddf707eab85bfa6cf01a6fe2522634a
+size 14567

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b53323acb2950ba4d2cebb5543fb4bef75fc782b28736088a1b9b0f0221e248
+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 +1,408 @@
+{
+  "best_metric": 2.670438766479492,
+  "best_model_checkpoint": "output/bob-dylan/checkpoint-321",
+  "epoch": 1.0,
+  "global_step": 321,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00013711788223044424,
+      "loss": 3.6967,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001368717255202631,
+      "loss": 3.7692,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00013646211919423798,
+      "loss": 3.4916,
+      "step": 15
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00013589004389254062,
+      "loss": 3.6186,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00013515686922297834,
+      "loss": 3.5756,
+      "step": 25
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00013426435048201062,
+      "loss": 3.236,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0001332146244523866,
+      "loss": 3.3956,
+      "step": 35
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00013201020428746477,
+      "loss": 3.3277,
+      "step": 40
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0001306539734944624,
+      "loss": 3.2617,
+      "step": 45
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00012914917903103908,
+      "loss": 3.554,
+      "step": 50
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00012749942353174222,
+      "loss": 3.2625,
+      "step": 55
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00012570865668292503,
+      "loss": 3.2986,
+      "step": 60
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001237811657667863,
+      "loss": 3.264,
+      "step": 65
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00012172156539717071,
+      "loss": 3.0437,
+      "step": 70
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00011953478647170303,
+      "loss": 3.0527,
+      "step": 75
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.000117226064366706,
+      "loss": 3.3623,
+      "step": 80
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0001148009264031647,
+      "loss": 3.0801,
+      "step": 85
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0001122651786137447,
+      "loss": 3.0471,
+      "step": 90
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00010962489184254581,
+      "loss": 3.051,
+      "step": 95
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00010688638721086951,
+      "loss": 3.2191,
+      "step": 100
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0001040562209837965,
+      "loss": 2.9343,
+      "step": 105
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00010114116887380613,
+      "loss": 2.9893,
+      "step": 110
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.814820981901533e-05,
+      "loss": 3.1068,
+      "step": 115
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.508450927487455e-05,
+      "loss": 3.1636,
+      "step": 120
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.195740205932179e-05,
+      "loss": 3.1864,
+      "step": 125
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.877437479246497e-05,
+      "loss": 2.9116,
+      "step": 130
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.554304797283438e-05,
+      "loss": 3.1795,
+      "step": 135
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.227115773311617e-05,
+      "loss": 2.9074,
+      "step": 140
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 7.896653731904552e-05,
+      "loss": 3.1763,
+      "step": 145
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.56370983358012e-05,
+      "loss": 3.0588,
+      "step": 150
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.229081180679942e-05,
+      "loss": 2.9373,
+      "step": 155
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 6.893568909023427e-05,
+      "loss": 3.092,
+      "step": 160
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 6.557976269905237e-05,
+      "loss": 3.0733,
+      "step": 165
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 6.223106707028106e-05,
+      "loss": 2.9187,
+      "step": 170
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 5.889761932974993e-05,
+      "loss": 2.9659,
+      "step": 175
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5.5587400098257335e-05,
+      "loss": 3.1799,
+      "step": 180
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 5.230833438513365e-05,
+      "loss": 2.9959,
+      "step": 185
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.9068272614944106e-05,
+      "loss": 2.8529,
+      "step": 190
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.58749718327555e-05,
+      "loss": 3.0337,
+      "step": 195
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.2736077132963006e-05,
+      "loss": 3.0827,
+      "step": 200
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.9659103356138536e-05,
+      "loss": 2.8453,
+      "step": 205
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.6651417097720435e-05,
+      "loss": 2.9619,
+      "step": 210
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.372021907161731e-05,
+      "loss": 3.0061,
+      "step": 215
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.0872526870949537e-05,
+      "loss": 2.8687,
+      "step": 220
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.8115158167201102e-05,
+      "loss": 2.9913,
+      "step": 225
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.5454714388004492e-05,
+      "loss": 2.9778,
+      "step": 230
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2.289756491263597e-05,
+      "loss": 3.0748,
+      "step": 235
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.0449831823058788e-05,
+      "loss": 2.7658,
+      "step": 240
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.8117375247021725e-05,
+      "loss": 2.9792,
+      "step": 245
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.5905779328303487e-05,
+      "loss": 2.7718,
+      "step": 250
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3820338857691364e-05,
+      "loss": 2.9954,
+      "step": 255
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.1866046596701035e-05,
+      "loss": 2.9246,
+      "step": 260
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.0047581324385938e-05,
+      "loss": 2.9875,
+      "step": 265
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.36929663585326e-06,
+      "loss": 2.673,
+      "step": 270
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.835210519304257e-06,
+      "loss": 2.8515,
+      "step": 275
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5.448995736552248e-06,
+      "loss": 2.9416,
+      "step": 280
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 4.213971030048682e-06,
+      "loss": 2.8573,
+      "step": 285
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.133093177468323e-06,
+      "loss": 2.6045,
+      "step": 290
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.208949912875789e-06,
+      "loss": 3.0414,
+      "step": 295
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.4437537314208725e-06,
+      "loss": 2.7666,
+      "step": 300
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 8.39336592394954e-07,
+      "loss": 2.7331,
+      "step": 305
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.971455333297437e-07,
+      "loss": 2.847,
+      "step": 310
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.1823920563887646e-07,
+      "loss": 2.7128,
+      "step": 315
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.2853400962779e-09,
+      "loss": 2.6074,
+      "step": 320
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.670438766479492,
+      "eval_runtime": 18.6137,
+      "eval_samples_per_second": 22.833,
+      "eval_steps_per_second": 2.901,
+      "step": 321
+    }
+  ],
+  "max_steps": 321,
+  "num_train_epochs": 1,
+  "total_flos": 334715092992000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db9354963730efbedcdb8b2504ec8c8be69bbb41ca7f3848c146dad268008e05
+size 2863