huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/mf-doom
+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/263743633b6e58854e753b25dca6beab.430x430x1.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">MF DOOM</div>
+    <a href="https://genius.com/artists/mf-doom">
+    	<div style="text-align: center; font-size: 14px;">@mf-doom</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 MF DOOM.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/mf-doom).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/mf-doom")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3lhrsfds/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 MF DOOM's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/vw48qbeh) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/vw48qbeh/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/mf-doom')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/mf-doom")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/mf-doom")
+```
+
+## 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": "4.10.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 4.393705368041992, "eval_runtime": 13.509, "eval_samples_per_second": 22.281, "eval_steps_per_second": 2.813, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fea913f65e5d26fb478026522c1c01c422c07a137299fed0927d328941b1616a
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e918e098ec86ee79b01188511c6e65f6f48de64fc07a3224dd90a577978ffbdf
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0365b17ba0409407c269ab7d327a5df4c4d412f8dadfe4c2d5245b807c3883bf
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9ea39532e0f5bc48b00bc01a94eb8460df3f5e7e6c24f13e1aee73a6e86adf7
+size 14567

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f25c6cf4b179ff877fb4760c2e926f8db770ae39533e18946954287fb7283de
+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 +1,252 @@
+{
+  "best_metric": 4.393705368041992,
+  "best_model_checkpoint": "output/mf-doom/checkpoint-193",
+  "epoch": 1.0,
+  "global_step": 193,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013697291967368176,
+      "loss": 4.7696,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001362931820613334,
+      "loss": 4.9375,
+      "step": 10
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00013516528730985944,
+      "loss": 4.6377,
+      "step": 15
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00013359670255361022,
+      "loss": 4.7907,
+      "step": 20
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00013159781247883373,
+      "loss": 4.8492,
+      "step": 25
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00012918185057271526,
+      "loss": 4.698,
+      "step": 30
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00012636481151216485,
+      "loss": 4.6354,
+      "step": 35
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0001231653452723755,
+      "loss": 4.7479,
+      "step": 40
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00011960463365619783,
+      "loss": 4.6099,
+      "step": 45
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.000115706250061758,
+      "loss": 4.4771,
+      "step": 50
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.000111496003416716,
+      "loss": 4.6176,
+      "step": 55
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00010700176731238488,
+      "loss": 4.5517,
+      "step": 60
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00010225329546891398,
+      "loss": 4.6173,
+      "step": 65
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.728202475323418e-05,
+      "loss": 4.5918,
+      "step": 70
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.21208670538683e-05,
+      "loss": 4.4796,
+      "step": 75
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.680399139048255e-05,
+      "loss": 4.5046,
+      "step": 80
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.136659770070481e-05,
+      "loss": 4.5786,
+      "step": 85
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.584468380183525e-05,
+      "loss": 4.5974,
+      "step": 90
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.027480707026031e-05,
+      "loss": 4.4949,
+      "step": 95
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 6.469384241635202e-05,
+      "loss": 4.5468,
+      "step": 100
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 5.9138738157159314e-05,
+      "loss": 4.2671,
+      "step": 105
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.364627140311692e-05,
+      "loss": 4.5739,
+      "step": 110
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.825280457821314e-05,
+      "loss": 4.4114,
+      "step": 115
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.299404468555545e-05,
+      "loss": 4.403,
+      "step": 120
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.7904806912095865e-05,
+      "loss": 4.5395,
+      "step": 125
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.30187841375518e-05,
+      "loss": 4.478,
+      "step": 130
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.8368323873469696e-05,
+      "loss": 4.5482,
+      "step": 135
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2.39842141091877e-05,
+      "loss": 4.5102,
+      "step": 140
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.9895479482486794e-05,
+      "loss": 4.3508,
+      "step": 145
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.61291891243658e-05,
+      "loss": 4.3784,
+      "step": 150
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.2710277450088041e-05,
+      "loss": 4.5042,
+      "step": 155
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.661379082937688e-06,
+      "loss": 4.3445,
+      "step": 160
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.002679003559785e-06,
+      "loss": 4.5091,
+      "step": 165
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.7517789169574735e-06,
+      "loss": 4.4888,
+      "step": 170
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.9235807218530457e-06,
+      "loss": 4.354,
+      "step": 175
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.5301878538942795e-06,
+      "loss": 4.3435,
+      "step": 180
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 5.808251558551173e-07,
+      "loss": 4.3824,
+      "step": 185
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 8.177780532344056e-08,
+      "loss": 4.4941,
+      "step": 190
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 4.393705368041992,
+      "eval_runtime": 13.4209,
+      "eval_samples_per_second": 22.428,
+      "eval_steps_per_second": 2.831,
+      "step": 193
+    }
+  ],
+  "max_steps": 193,
+  "num_train_epochs": 1,
+  "total_flos": 201586802688000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7278a1b136997246e7ae5fefc9c53f26e3f1c34248a2305667b9ad8fcd9cc82e
+size 2671