huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/nervy
+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/690c7ea858696b779e94dc99b204f034.1000x1000x1.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">Нервы (Nervy)</div>
+    <a href="https://genius.com/artists/nervy">
+    	<div style="text-align: center; font-size: 14px;">@nervy</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 Нервы (Nervy).
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/nervy).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/nervy")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/34zj7k43/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 Нервы (Nervy)'s lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2pd7k5jf) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2pd7k5jf/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/nervy')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/nervy")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/nervy")
+```
+
+## 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": 1.716844081878662, "eval_runtime": 2.1998, "eval_samples_per_second": 40.458, "eval_steps_per_second": 5.455, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c8e300d688f76c22d7721e19ef78d1116dbbf4feeb5c25db76dfe34d0a2574
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df2a699613d093a0c93bf0ad685dba475b8c1f33aa09d05ccb11e61efa596239
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efb7bef509d76c886e75f4d1b3b174a6a066ffbc606fd9f49da41fd2ea098ad8
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5b589435e7c1854c0fa4a70401b6912419ec76dc23e228934fca77f5d458ddf
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bff01c22e594ae300be4b08662691395a148cdb6d4ed4273d76a8d9526d2945c
+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 +1,102 @@
+{
+  "best_metric": 1.716844081878662,
+  "best_model_checkpoint": "output/nervy/checkpoint-67",
+  "epoch": 1.0,
+  "global_step": 67,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00013532330330528217,
+      "loss": 2.4761,
+      "step": 5
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00012979589515943672,
+      "loss": 2.0363,
+      "step": 10
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001209202032183722,
+      "loss": 2.0351,
+      "step": 15
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00010918185377156764,
+      "loss": 1.8591,
+      "step": 20
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.522310109331633e-05,
+      "loss": 1.6691,
+      "step": 25
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 7.980768702075116e-05,
+      "loss": 1.7511,
+      "step": 30
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 6.377905343835293e-05,
+      "loss": 1.8029,
+      "step": 35
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.8014194038976637e-05,
+      "loss": 1.8511,
+      "step": 40
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.337567032488183e-05,
+      "loss": 1.7338,
+      "step": 45
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.0664417254371463e-05,
+      "loss": 1.9426,
+      "step": 50
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.0575920734825916e-05,
+      "loss": 1.8186,
+      "step": 55
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.66216467507622e-06,
+      "loss": 1.9079,
+      "step": 60
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.014296332977907e-07,
+      "loss": 1.8372,
+      "step": 65
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.716844081878662,
+      "eval_runtime": 2.1609,
+      "eval_samples_per_second": 41.187,
+      "eval_steps_per_second": 5.553,
+      "step": 67
+    }
+  ],
+  "max_steps": 67,
+  "num_train_epochs": 1,
+  "total_flos": 69764972544000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13d0232535fc6650de1d656343f21cd4137967ed9e1334f5c09ac9aadc90ba10
+size 2671