huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/yung-lean
+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/8c898f8c39dbd271b3ccfd5303d423c7.1000x1000x1.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">Yung Lean</div>
+    <a href="https://genius.com/artists/yung-lean">
+    	<div style="text-align: center; font-size: 14px;">@yung-lean</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 Yung Lean.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/yung-lean).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/yung-lean")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3mtv3swy/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 Yung Lean's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1qh8r5pu) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1qh8r5pu/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/yung-lean')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/yung-lean")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/yung-lean")
+```
+
+## 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 +1,40 @@
+{
+  "_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,
+  "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": "4.11.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 3.4337549209594727, "eval_runtime": 0.926, "eval_samples_per_second": 75.597, "eval_steps_per_second": 9.72, "epoch": 60.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2bd687dcdbd5eea9e94c4e450dcc4fb341850b8a500cbf94b00059a55fe64c
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:597fb30f61ce33299ff7a984293f74986e7776f1e949b45d8f474aa24980fc58
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07d722be0b4138a98cec34cdc0088c9508369427121eb35174889cd967f3346d
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:055e64f836f6108839b4cfede0711df0727829df6e7a209dc5cae46b41b9cd33
+size 14567

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ce1132cbb6aa5c18263e33796f9990b4148f45c42e80bbd2185f1d18ecd3d7
+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 +1,208 @@
+{
+  "best_metric": 3.4337549209594727,
+  "best_model_checkpoint": "output/yung-lean/checkpoint-144",
+  "epoch": 3.0,
+  "global_step": 144,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00013355940688336427,
+      "loss": 3.9118,
+      "step": 5
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00012302403914397873,
+      "loss": 3.761,
+      "step": 10
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00010671211798514472,
+      "loss": 3.6532,
+      "step": 15
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.635498649403293e-05,
+      "loss": 3.4509,
+      "step": 20
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 6.411334533481218e-05,
+      "loss": 3.5511,
+      "step": 25
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.2347916539754844e-05,
+      "loss": 3.6085,
+      "step": 30
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2.3368877084135277e-05,
+      "loss": 3.2754,
+      "step": 35
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.190657300387505e-06,
+      "loss": 3.5324,
+      "step": 40
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.3181297643383925e-06,
+      "loss": 3.2119,
+      "step": 45
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.5056326389312744,
+      "eval_runtime": 0.9143,
+      "eval_samples_per_second": 76.563,
+      "eval_steps_per_second": 9.844,
+      "step": 48
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 5.868825097566078e-07,
+      "loss": 3.5151,
+      "step": 50
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 7.074529930857578e-06,
+      "loss": 3.3697,
+      "step": 55
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.009247481060283e-05,
+      "loss": 3.4438,
+      "step": 60
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 3.825899585097651e-05,
+      "loss": 3.1986,
+      "step": 65
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 5.964590321370446e-05,
+      "loss": 3.0037,
+      "step": 70
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 8.19831960903064e-05,
+      "loss": 3.336,
+      "step": 75
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00010290000000000001,
+      "loss": 3.4818,
+      "step": 80
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.00012017621079305782,
+      "loss": 3.2708,
+      "step": 85
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00013197813593027427,
+      "loss": 3.0245,
+      "step": 90
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.0001370531221341682,
+      "loss": 3.1731,
+      "step": 95
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.4461593627929688,
+      "eval_runtime": 0.9154,
+      "eval_samples_per_second": 76.473,
+      "eval_steps_per_second": 9.832,
+      "step": 96
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 0.00013486251168343008,
+      "loss": 3.1258,
+      "step": 100
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.0001256388154039546,
+      "loss": 3.0698,
+      "step": 105
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 0.00011036103402999826,
+      "loss": 2.9638,
+      "step": 110
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 9.065074731979686e-05,
+      "loss": 2.9622,
+      "step": 115
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 6.860000000000001e-05,
+      "loss": 2.9506,
+      "step": 120
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 4.6549252680203134e-05,
+      "loss": 2.9087,
+      "step": 125
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 2.683896597000177e-05,
+      "loss": 2.9057,
+      "step": 130
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.1561184596045404e-05,
+      "loss": 2.9869,
+      "step": 135
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 2.337488316569914e-06,
+      "loss": 2.9926,
+      "step": 140
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.4337549209594727,
+      "eval_runtime": 0.9131,
+      "eval_samples_per_second": 76.662,
+      "eval_steps_per_second": 9.857,
+      "step": 144
+    }
+  ],
+  "max_steps": 2880,
+  "num_train_epochs": 60,
+  "total_flos": 149328396288000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ac7169a2bc4c30c8665b103238bd6f0a6372cdb36e9413b0afaa978684ac9fb
+size 2863