huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/21-savage
+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/aa32202cc20d1dde62e57940a8b278b2.770x770x1.png&#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">21 Savage</div>
+    <a href="https://genius.com/artists/21-savage">
+    	<div style="text-align: center; font-size: 14px;">@21-savage</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 21 Savage.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/21-savage).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/21-savage")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3lbkznnf/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 21 Savage's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1fw9b6m4) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1fw9b6m4/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/21-savage')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/21-savage")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/21-savage")
+```
+
+## 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": 3.3079917430877686, "eval_runtime": 7.3059, "eval_samples_per_second": 21.763, "eval_steps_per_second": 2.738, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3160451597c8c0e231d1b394a7a656221ee9f217fada38d17988298d2181939
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2c77fd94d25f8e9f6f8b8d4b881368aa15faa5a41b03a1eff18620933bc27ae
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94e0c2c88d1207e023438b0ee58995c99f2bfa4f0d4e3abc303d8b2adee62ac6
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6bb1b10a8a221d72982ac43c9a106dffcd7d0180022cece4ed59f4cfa97e390
+size 14567

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e4dbdf06ece825665196e07e0bc1bd50d0d87f6015cbb9ec4b10742a7104e71
+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": 3.3079917430877686,
+  "best_model_checkpoint": "output/21-savage/checkpoint-128",
+  "epoch": 1.0,
+  "global_step": 128,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0001366840960734715,
+      "loss": 3.9729,
+      "step": 5
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00013514414396914573,
+      "loss": 3.8142,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001326033060000631,
+      "loss": 3.5999,
+      "step": 15
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00012909979873429716,
+      "loss": 3.5616,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00012468631818219865,
+      "loss": 3.5237,
+      "step": 25
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00011942924719935021,
+      "loss": 3.3237,
+      "step": 30
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011340765702662907,
+      "loss": 3.5837,
+      "step": 35
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00010671211798514472,
+      "loss": 3.5472,
+      "step": 40
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.944333721430602e-05,
+      "loss": 3.3629,
+      "step": 45
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.171064394270629e-05,
+      "loss": 3.5192,
+      "step": 50
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.363034507476126e-05,
+      "loss": 3.423,
+      "step": 55
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.532397582660788e-05,
+      "loss": 3.602,
+      "step": 60
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 6.691647172332823e-05,
+      "loss": 3.3109,
+      "step": 65
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 5.853428945236219e-05,
+      "loss": 3.4656,
+      "step": 70
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 5.0303504837221976e-05,
+      "loss": 3.261,
+      "step": 75
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.2347916539754844e-05,
+      "loss": 3.3219,
+      "step": 80
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.478718401303682e-05,
+      "loss": 3.2217,
+      "step": 85
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.773502771181907e-05,
+      "loss": 3.3141,
+      "step": 90
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.1297518631037208e-05,
+      "loss": 3.2947,
+      "step": 95
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.557148289931624e-05,
+      "loss": 3.3889,
+      "step": 100
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.0643045423870092e-05,
+      "loss": 3.3058,
+      "step": 105
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.586334491731787e-06,
+      "loss": 3.3431,
+      "step": 110
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.462366811317684e-06,
+      "loss": 3.3222,
+      "step": 115
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.3181297643383925e-06,
+      "loss": 3.2589,
+      "step": 120
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.858746718418518e-07,
+      "loss": 3.3423,
+      "step": 125
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.3079917430877686,
+      "eval_runtime": 7.1911,
+      "eval_samples_per_second": 22.111,
+      "eval_steps_per_second": 2.781,
+      "step": 128
+    }
+  ],
+  "max_steps": 128,
+  "num_train_epochs": 1,
+  "total_flos": 132997644288000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:316f40a6914ef4bb45840ab66ed2d0ca4574b9c4fc145a735e6b2f69b8e9f4f2
+size 2671