huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/logic
+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/0f975524d106026e89de983689d007c4.900x900x1.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">Logic</div>
+    <a href="https://genius.com/artists/logic">
+    	<div style="text-align: center; font-size: 14px;">@logic</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 Logic.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/logic).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/logic")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2rp89nd3/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 Logic's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/25a9752b) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/25a9752b/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/logic')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/logic")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/logic")
+```
+
+## 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": "4.10.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 3.4699020385742188, "eval_runtime": 11.125, "eval_samples_per_second": 22.562, "eval_steps_per_second": 2.876, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dc3a9f2fde73f2c08595112c12c12a0dee5f68e782883fe3c32f13748511ba1
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:144726cd4d0fa959abdac426d75b2861bad42927716be05e333a18b3dabd4374
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4395c1150c15382c37b060d3b31c82ff3f4c7e8a297322e3d198bfe584b01604
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61345b22ba347c8b1ef180579c39f41d6cf8392c8da3975e51bcbe95f65b549b
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55aace16bb0094b34bccf48434f50e6c8493d4dbe00f21e9e0c5d6ccf64cd4da
+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 +1,222 @@
+{
+  "best_metric": 3.4699020385742188,
+  "best_model_checkpoint": "output/logic/checkpoint-166",
+  "epoch": 1.0,
+  "global_step": 166,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013689310231466715,
+      "loss": 4.1499,
+      "step": 5
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001359751552117083,
+      "loss": 3.8329,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001344543719809531,
+      "loss": 3.9919,
+      "step": 15
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00013234435976098498,
+      "loss": 3.6771,
+      "step": 20
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00012966399778988942,
+      "loss": 3.7582,
+      "step": 25
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00012643726848413238,
+      "loss": 3.8118,
+      "step": 30
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0001226930428569831,
+      "loss": 3.6305,
+      "step": 35
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00011846482219643966,
+      "loss": 3.8223,
+      "step": 40
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011379043831398306,
+      "loss": 3.7137,
+      "step": 45
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00010871171504616964,
+      "loss": 3.8248,
+      "step": 50
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00010327409403776145,
+      "loss": 3.5061,
+      "step": 55
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.752622815468262e-05,
+      "loss": 3.5028,
+      "step": 60
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.151954616472095e-05,
+      "loss": 3.599,
+      "step": 65
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.530779258097404e-05,
+      "loss": 3.5615,
+      "step": 70
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 7.894654678527026e-05,
+      "loss": 3.7261,
+      "step": 75
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.249272573418489e-05,
+      "loss": 3.6186,
+      "step": 80
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 6.600407469716782e-05,
+      "loss": 3.6312,
+      "step": 85
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 5.9538650583379234e-05,
+      "loss": 3.4797,
+      "step": 90
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.315430248014319e-05,
+      "loss": 3.515,
+      "step": 95
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.6908154050877874e-05,
+      "loss": 3.7826,
+      "step": 100
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.0856092423722846e-05,
+      "loss": 3.3625,
+      "step": 105
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.505226814400944e-05,
+      "loss": 3.5743,
+      "step": 110
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 2.954861066472669e-05,
+      "loss": 3.6889,
+      "step": 115
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.4394363710109435e-05,
+      "loss": 3.5212,
+      "step": 120
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.963564466966226e-05,
+      "loss": 3.5788,
+      "step": 125
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.5315031964920546e-05,
+      "loss": 3.3559,
+      "step": 130
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.1471184080966003e-05,
+      "loss": 3.4134,
+      "step": 135
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.138493671395088e-06,
+      "loss": 3.6262,
+      "step": 140
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5.34677983161971e-06,
+      "loss": 3.577,
+      "step": 145
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.121021293871321e-06,
+      "loss": 3.3871,
+      "step": 150
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.4811329311337175e-06,
+      "loss": 3.5072,
+      "step": 155
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.4178756972551454e-07,
+      "loss": 3.5187,
+      "step": 160
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.2284704855989247e-08,
+      "loss": 3.5082,
+      "step": 165
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.4699020385742188,
+      "eval_runtime": 10.9862,
+      "eval_samples_per_second": 22.847,
+      "eval_steps_per_second": 2.913,
+      "step": 166
+    }
+  ],
+  "max_steps": 166,
+  "num_train_epochs": 1,
+  "total_flos": 172844679168000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337ba6e35302b0d7d46f48c59c1da3091c08327f58d3f4921d65e47268a283b8
+size 2671