huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/lil-uzi-vert
+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/73f52f6c73859a68ab961ca797e7b848.725x725x1.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 Uzi Vert</div>
+    <a href="https://genius.com/artists/lil-uzi-vert">
+    	<div style="text-align: center; font-size: 14px;">@lil-uzi-vert</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 Uzi Vert.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/lil-uzi-vert).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/lil-uzi-vert")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2ndgi0dn/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 Uzi Vert's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/9x6wbf6e) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/9x6wbf6e/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-uzi-vert')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/lil-uzi-vert")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/lil-uzi-vert")
+```
+
+## 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": "4.9.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 3.0165445804595947, "eval_runtime": 8.1174, "eval_samples_per_second": 37.45, "eval_steps_per_second": 4.681, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9f834e2dab17d6b22f3e5622e6ae587c757af1be1061e4ecc23e0724ae0b559
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42921bfbd1f7da4499f0e2f798f9137b868407cced67116b7819ce354a30349b
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e18a4078f8a9380fdeeb65a2e0038b5134dea4b4c76336a114ed08cea4d5ffa2
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3498d3c2707018f535ef83533e9dc2d6c4d547651de1f61798ba34c842d4d7f0
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbcce13fecbcb2be23ea34670a937a2c27e28ac198853dd41e256aa3ed115744
+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 +1,282 @@
+{
+  "best_metric": 3.0165445804595947,
+  "best_model_checkpoint": "output/lil-uzi-vert/checkpoint-218",
+  "epoch": 1.0,
+  "global_step": 218,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001370219946819302,
+      "loss": 4.0012,
+      "step": 5
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001364889025146963,
+      "loss": 3.8869,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00013560349006508517,
+      "loss": 3.6034,
+      "step": 15
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001343703523221556,
+      "loss": 3.5643,
+      "step": 20
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00013279588885081002,
+      "loss": 3.3069,
+      "step": 25
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0001308882705802323,
+      "loss": 3.431,
+      "step": 30
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00012865739739954807,
+      "loss": 3.5848,
+      "step": 35
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00012611484678077197,
+      "loss": 3.4069,
+      "step": 40
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00012327381369567084,
+      "loss": 3.3532,
+      "step": 45
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00012014904213835435,
+      "loss": 3.4164,
+      "step": 50
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011675674860896696,
+      "loss": 3.5117,
+      "step": 55
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00011311453795557528,
+      "loss": 3.2964,
+      "step": 60
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00010924131201100248,
+      "loss": 3.2104,
+      "step": 65
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00010515717149875347,
+      "loss": 3.0675,
+      "step": 70
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00010088331171710597,
+      "loss": 3.4575,
+      "step": 75
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.644191254273106e-05,
+      "loss": 3.1265,
+      "step": 80
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.185602332468734e-05,
+      "loss": 3.3004,
+      "step": 85
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.714944326614944e-05,
+      "loss": 3.2766,
+      "step": 90
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.234659791464919e-05,
+      "loss": 3.1492,
+      "step": 95
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 7.747241240180272e-05,
+      "loss": 3.3842,
+      "step": 100
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.255218209036649e-05,
+      "loss": 3.3591,
+      "step": 105
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 6.76114412999196e-05,
+      "loss": 3.1375,
+      "step": 110
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 6.267583079244174e-05,
+      "loss": 3.2619,
+      "step": 115
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 5.777096470549132e-05,
+      "loss": 3.1689,
+      "step": 120
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.2922297623555134e-05,
+      "loss": 3.264,
+      "step": 125
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.815499247742428e-05,
+      "loss": 3.0831,
+      "step": 130
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.349378995715337e-05,
+      "loss": 3.1357,
+      "step": 135
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.896288011630533e-05,
+      "loss": 3.164,
+      "step": 140
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.458577683381209e-05,
+      "loss": 3.2134,
+      "step": 145
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.0385195784951376e-05,
+      "loss": 3.1053,
+      "step": 150
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.63829365547284e-05,
+      "loss": 3.099,
+      "step": 155
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2.2599769505454377e-05,
+      "loss": 3.1365,
+      "step": 160
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.905532798564004e-05,
+      "loss": 3.1402,
+      "step": 165
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.5768006439603532e-05,
+      "loss": 3.1203,
+      "step": 170
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.2754864946569404e-05,
+      "loss": 3.2424,
+      "step": 175
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.0031540684667541e-05,
+      "loss": 3.2244,
+      "step": 180
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.612166779304597e-06,
+      "loss": 3.2007,
+      "step": 185
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5.5092989570564855e-06,
+      "loss": 3.0923,
+      "step": 190
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.7338503857237188e-06,
+      "loss": 3.0841,
+      "step": 195
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.295035038707367e-06,
+      "loss": 3.1703,
+      "step": 200
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.2003198776252066e-06,
+      "loss": 3.2195,
+      "step": 205
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.5538610132401196e-07,
+      "loss": 3.0425,
+      "step": 210
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.409966239244377e-08,
+      "loss": 3.1853,
+      "step": 215
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.0165445804595947,
+      "eval_runtime": 8.1641,
+      "eval_samples_per_second": 37.236,
+      "eval_steps_per_second": 4.655,
+      "step": 218
+    }
+  ],
+  "max_steps": 218,
+  "num_train_epochs": 1,
+  "total_flos": 227454713856000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32eed4e7cdcf3d9611cb0954dec030a5a9f6c10f458a381c5e5a079e5eb26127
+size 2671