huggingartists

README.md

@@ -0,0 +1,91 @@
+---
+language: en
+datasets:
+- huggingartists/drake
+tags:
+- huggingartists
+- lyrics
+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/c6b5142a09ff5bd361d0f42a55692edc.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">Drake</div>
+    <a href="https://genius.com/artists/drake">
+    	<div style="text-align: center; font-size: 14px;">@drake</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 Drake.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/drake).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/drake")
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/drake")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/drake")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1ba7t9q0/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 Drake's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/18yhidb2) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/18yhidb2/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/drake')
+generator("I am", num_return_sequences=5)
+```
+
+## 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)
+
+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": "4.9.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f54b613b898ec9cd602b10294cad4372affedb9070359bf8fb1e1efc0c38351b
+size 995604017

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d646844d7a1967fa54609f85a5452b8eae50cafd2f88c1e934be317c5f71252
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c479098b6ff1a7d6e1a01f9b8d8a54011a8cc009f5aa71d8d828ce9e600a222
+size 14567

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dab3de057a89d68db2661a52fbf111edc97698719020db0127718fdc9badb3d
+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 +1,478 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 386,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001371432064088578,
+      "loss": 4.0588,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013697291967368176,
+      "loss": 3.874,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.000136689421753516,
+      "loss": 3.7354,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001362931820613334,
+      "loss": 3.678,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00013578485668678617,
+      "loss": 3.4762,
+      "step": 25
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00013516528730985944,
+      "loss": 3.9075,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.000134435499807226,
+      "loss": 3.8826,
+      "step": 35
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00013359670255361022,
+      "loss": 3.6832,
+      "step": 40
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00013265028442097337,
+      "loss": 3.5663,
+      "step": 45
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00013159781247883373,
+      "loss": 3.875,
+      "step": 50
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00013044102939952857,
+      "loss": 3.6027,
+      "step": 55
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00012918185057271526,
+      "loss": 3.7132,
+      "step": 60
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001278223609338884,
+      "loss": 3.5338,
+      "step": 65
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00012636481151216485,
+      "loss": 3.8949,
+      "step": 70
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0001248116157030527,
+      "loss": 3.5964,
+      "step": 75
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0001231653452723755,
+      "loss": 3.7202,
+      "step": 80
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00012142872609796847,
+      "loss": 3.6172,
+      "step": 85
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00011960463365619783,
+      "loss": 3.4145,
+      "step": 90
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011769608826077622,
+      "loss": 3.555,
+      "step": 95
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.000115706250061758,
+      "loss": 3.4485,
+      "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011363841381299484,
+      "loss": 3.7157,
+      "step": 105
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.000111496003416716,
+      "loss": 3.6139,
+      "step": 110
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0001092825662542656,
+      "loss": 3.6335,
+      "step": 115
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00010700176731238488,
+      "loss": 3.8618,
+      "step": 120
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00010465738311476428,
+      "loss": 3.5889,
+      "step": 125
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00010225329546891398,
+      "loss": 3.5039,
+      "step": 130
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.979348503870657e-05,
+      "loss": 3.456,
+      "step": 135
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.728202475323418e-05,
+      "loss": 3.5593,
+      "step": 140
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.472307306289397e-05,
+      "loss": 3.6619,
+      "step": 145
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.21208670538683e-05,
+      "loss": 3.2545,
+      "step": 150
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.94797154324004e-05,
+      "loss": 3.5664,
+      "step": 155
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.680399139048255e-05,
+      "loss": 3.6659,
+      "step": 160
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.409812536476914e-05,
+      "loss": 3.4141,
+      "step": 165
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.136659770070481e-05,
+      "loss": 3.3853,
+      "step": 170
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 7.86139312340139e-05,
+      "loss": 3.5356,
+      "step": 175
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.584468380183525e-05,
+      "loss": 3.6393,
+      "step": 180
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.306344069590158e-05,
+      "loss": 3.7593,
+      "step": 185
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.027480707026031e-05,
+      "loss": 3.6784,
+      "step": 190
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 6.748340031610621e-05,
+      "loss": 3.4365,
+      "step": 195
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 6.469384241635202e-05,
+      "loss": 3.4692,
+      "step": 200
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 6.191075229259615e-05,
+      "loss": 3.5463,
+      "step": 205
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 5.9138738157159314e-05,
+      "loss": 3.4183,
+      "step": 210
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5.638238988285346e-05,
+      "loss": 3.6126,
+      "step": 215
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.364627140311692e-05,
+      "loss": 3.5828,
+      "step": 220
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 5.093491315510001e-05,
+      "loss": 3.4454,
+      "step": 225
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.825280457821314e-05,
+      "loss": 3.5058,
+      "step": 230
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.560438668055879e-05,
+      "loss": 3.4436,
+      "step": 235
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.299404468555545e-05,
+      "loss": 3.3312,
+      "step": 240
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.042610077092918e-05,
+      "loss": 3.4519,
+      "step": 245
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.7904806912095865e-05,
+      "loss": 3.2724,
+      "step": 250
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.543433784178337e-05,
+      "loss": 3.708,
+      "step": 255
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.30187841375518e-05,
+      "loss": 3.3732,
+      "step": 260
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.06621454486565e-05,
+      "loss": 3.6682,
+      "step": 265
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 2.8368323873469696e-05,
+      "loss": 3.3303,
+      "step": 270
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.614111749842566e-05,
+      "loss": 3.4287,
+      "step": 275
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2.39842141091877e-05,
+      "loss": 3.4274,
+      "step": 280
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.1901185084450396e-05,
+      "loss": 3.3246,
+      "step": 285
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.9895479482486794e-05,
+      "loss": 3.4282,
+      "step": 290
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.7970418330233093e-05,
+      "loss": 3.2375,
+      "step": 295
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.61291891243658e-05,
+      "loss": 3.581,
+      "step": 300
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.4374840553477238e-05,
+      "loss": 3.42,
+      "step": 305
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.2710277450088041e-05,
+      "loss": 3.4236,
+      "step": 310
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.1138255980854819e-05,
+      "loss": 3.3657,
+      "step": 315
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.661379082937688e-06,
+      "loss": 3.1107,
+      "step": 320
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.282092154083231e-06,
+      "loss": 3.3076,
+      "step": 325
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.002679003559785e-06,
+      "loss": 3.3086,
+      "step": 330
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5.825258070649407e-06,
+      "loss": 3.3643,
+      "step": 335
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.7517789169574735e-06,
+      "loss": 3.348,
+      "step": 340
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.7840189983485763e-06,
+      "loss": 3.391,
+      "step": 345
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.9235807218530457e-06,
+      "loss": 3.2735,
+      "step": 350
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.171888792417796e-06,
+      "loss": 3.576,
+      "step": 355
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.5301878538942795e-06,
+      "loss": 3.2583,
+      "step": 360
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 9.995404281699138e-07,
+      "loss": 3.5956,
+      "step": 365
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 5.808251558551173e-07,
+      "loss": 3.7098,
+      "step": 370
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.7473534143910847e-07,
+      "loss": 3.3973,
+      "step": 375
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 8.177780532344056e-08,
+      "loss": 3.3842,
+      "step": 380
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.2720446338799106e-09,
+      "loss": 3.2786,
+      "step": 385
+    }
+  ],
+  "max_steps": 386,
+  "num_train_epochs": 1,
+  "total_flos": 403042959360000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:781ffb618640ff70dd3baac13df255d8dc426f031550cac003228fcbafce41fc
+size 2671