huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/lil-baby
+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/98367f3cd4548347b114452eb3a5927f.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">Lil Baby</div>
+    <a href="https://genius.com/artists/lil-baby">
+    	<div style="text-align: center; font-size: 14px;">@lil-baby</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 Lil Baby.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/lil-baby).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/lil-baby")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/vueaothh/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 Lil Baby's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/257bod1h) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/257bod1h/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/lil-baby')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/lil-baby")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/lil-baby")
+```
+
+## 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": 3.4053022861480713, "eval_runtime": 10.4291, "eval_samples_per_second": 22.245, "eval_steps_per_second": 2.781, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:580a9a0daf6fe0bdea3b325bb8296a000c03fb546a084ac95a5ed42a2f018934
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7049b8af8ce2c4a2150b8d3e9a336c60bc9bba3e530768a6e4fa827618a3e693
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:695edac1b4b1d2548cfcd164822af1c9f35d9ac8e7cefc77490faa9a6f4ad99e
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f523a442b4e6383ac7c0f2679920aeb03c184c22ff82e43ebf905f443e2141aa
+size 14567

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb71b8d9941063c635df32e061d21e647151549cf90fc9dd70cfed3b990a34f9
+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 +1,216 @@
+{
+  "best_metric": 3.4053022861480713,
+  "best_model_checkpoint": "output/lil-baby/checkpoint-161",
+  "epoch": 1.0,
+  "global_step": 161,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001368737597109298,
+      "loss": 4.1361,
+      "step": 5
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001358981418386525,
+      "loss": 3.9051,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00013428242585420812,
+      "loss": 3.9549,
+      "step": 15
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00013204197944418041,
+      "loss": 3.8706,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00012919811234281,
+      "loss": 3.6931,
+      "step": 25
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00012577787364704225,
+      "loss": 3.7356,
+      "step": 30
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001218137945423232,
+      "loss": 3.4819,
+      "step": 35
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011734357888617527,
+      "loss": 3.6124,
+      "step": 40
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00011240974459253048,
+      "loss": 3.3867,
+      "step": 45
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00010705921922774988,
+      "loss": 3.7457,
+      "step": 50
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00010134289366476881,
+      "loss": 3.4233,
+      "step": 55
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.531513804073266e-05,
+      "loss": 3.4982,
+      "step": 60
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.903328462203299e-05,
+      "loss": 3.4624,
+      "step": 65
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.255708249541069e-05,
+      "loss": 3.6589,
+      "step": 70
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.594812927176565e-05,
+      "loss": 3.5649,
+      "step": 75
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 6.926928520795311e-05,
+      "loss": 3.4196,
+      "step": 80
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 6.258407531907605e-05,
+      "loss": 3.5135,
+      "step": 85
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5.5956085168010344e-05,
+      "loss": 3.4432,
+      "step": 90
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.9448356079036955e-05,
+      "loss": 3.5893,
+      "step": 95
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.312278552793369e-05,
+      "loss": 3.554,
+      "step": 100
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.703953841164296e-05,
+      "loss": 3.5241,
+      "step": 105
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.125647479715328e-05,
+      "loss": 3.6419,
+      "step": 110
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.5828599592490882e-05,
+      "loss": 3.6566,
+      "step": 115
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.080753937420995e-05,
+      "loss": 3.5235,
+      "step": 120
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.624105134747227e-05,
+      "loss": 3.4856,
+      "step": 125
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.2172569109183958e-05,
+      "loss": 3.3829,
+      "step": 130
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.640789534607252e-06,
+      "loss": 3.4401,
+      "step": 135
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5.679304716725937e-06,
+      "loss": 3.2529,
+      "step": 140
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.3162824591277986e-06,
+      "loss": 3.4932,
+      "step": 145
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.574198361357997e-06,
+      "loss": 3.4635,
+      "step": 150
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.696220449804098e-07,
+      "loss": 3.4189,
+      "step": 155
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.3059553632214649e-08,
+      "loss": 3.3297,
+      "step": 160
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.4053022861480713,
+      "eval_runtime": 10.3203,
+      "eval_samples_per_second": 22.48,
+      "eval_steps_per_second": 2.81,
+      "step": 161
+    }
+  ],
+  "max_steps": 161,
+  "num_train_epochs": 1,
+  "total_flos": 167357546496000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7fe12374730690355046896bf7b157903263f59e8ad1749b3634ae7bc69236f
+size 2671