huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/boris-grebenshikov
+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/491c2f003f52c9837809b86faef7b764.1000x1000x1.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">Борис Гребенщиков (Boris Grebenshikov)</div>
+    <a href="https://genius.com/artists/boris-grebenshikov">
+    	<div style="text-align: center; font-size: 14px;">@boris-grebenshikov</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 Борис Гребенщиков (Boris Grebenshikov).
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/boris-grebenshikov).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/boris-grebenshikov")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/17fz2zsy/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 Борис Гребенщиков (Boris Grebenshikov)'s lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/31rj6k29) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/31rj6k29/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/boris-grebenshikov')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/boris-grebenshikov")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/boris-grebenshikov")
+```
+
+## 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": "4.10.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 1.8803279399871826, "eval_runtime": 11.6498, "eval_samples_per_second": 22.146, "eval_steps_per_second": 2.833, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a8f55a6dc86a57ae673545b08215bced477db9d2d2cd81be98fdbb18904000
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f36cc26900ca1466b9c88484f52c35f0b2d73669efd66a283ace9615cbba189
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdc01c8e9ac3f6ea36007a96f792a90996189530c114a4423b1b16d1d892899b
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3de7f451560a3fb6592fc184c9d1f804bb0cdb4ea9155d6284323d66d6063ab
+size 14567

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb7b588e7deba2b4499d6c6c3ea0e08b8017594086c1e44c612c131e26fdc94
+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": 1.8803279399871826,
+  "best_model_checkpoint": "output/boris-grebenshikov/checkpoint-169",
+  "epoch": 1.0,
+  "global_step": 169,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013690389360668606,
+      "loss": 2.5933,
+      "step": 5
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00013601813066569938,
+      "loss": 2.3572,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00013455035782630487,
+      "loss": 2.2816,
+      "step": 15
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00013251324613578177,
+      "loss": 2.2503,
+      "step": 20
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00012992438165230672,
+      "loss": 2.0864,
+      "step": 25
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00012680611362733682,
+      "loss": 2.1159,
+      "step": 30
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00012318536156811003,
+      "loss": 2.0993,
+      "step": 35
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00011909338284586077,
+      "loss": 1.8802,
+      "step": 40
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011456550285595239,
+      "loss": 2.0531,
+      "step": 45
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00010964081005941026,
+      "loss": 1.9281,
+      "step": 50
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0001043618185385132,
+      "loss": 2.1099,
+      "step": 55
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.877410097954656e-05,
+      "loss": 2.0119,
+      "step": 60
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.292589525111794e-05,
+      "loss": 1.9675,
+      "step": 65
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.686768797438203e-05,
+      "loss": 1.9512,
+      "step": 70
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.065177868014528e-05,
+      "loss": 2.047,
+      "step": 75
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.433182831541305e-05,
+      "loss": 1.9436,
+      "step": 80
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 6.796239599704895e-05,
+      "loss": 1.9677,
+      "step": 85
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 6.159846801167835e-05,
+      "loss": 1.8582,
+      "step": 90
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5.529498312790352e-05,
+      "loss": 1.9952,
+      "step": 95
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.9106358318734425e-05,
+      "loss": 1.9317,
+      "step": 100
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.3086018988597235e-05,
+      "loss": 1.834,
+      "step": 105
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.728593776039493e-05,
+      "loss": 1.8923,
+      "step": 110
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.1756185804197785e-05,
+      "loss": 1.9544,
+      "step": 115
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.6544500580870892e-05,
+      "loss": 1.921,
+      "step": 120
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.169587373223826e-05,
+      "loss": 1.9539,
+      "step": 125
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.725216267546246e-05,
+      "loss": 1.9665,
+      "step": 130
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3251729254682012e-05,
+      "loss": 2.0147,
+      "step": 135
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.729108569369736e-06,
+      "loss": 1.8575,
+      "step": 140
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.7147108383636075e-06,
+      "loss": 1.8372,
+      "step": 145
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 4.234558873329575e-06,
+      "loss": 1.7437,
+      "step": 150
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.310063428006295e-06,
+      "loss": 1.8886,
+      "step": 155
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 9.578383626055595e-07,
+      "loss": 1.9129,
+      "step": 160
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.895572190242788e-07,
+      "loss": 1.8767,
+      "step": 165
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.8803279399871826,
+      "eval_runtime": 11.5804,
+      "eval_samples_per_second": 22.279,
+      "eval_steps_per_second": 2.85,
+      "step": 169
+    }
+  ],
+  "max_steps": 169,
+  "num_train_epochs": 1,
+  "total_flos": 176110829568000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcecf49ff1760e04ac3d0e673c15ec03052622419263379f9a66e2ed277e9809
+size 2671