huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/gspd
+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/9409ae2b38424a74b42cb1e4bb66b83a.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">GSPD</div>
+    <a href="https://genius.com/artists/gspd">
+    	<div style="text-align: center; font-size: 14px;">@gspd</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 GSPD.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/gspd).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/gspd")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/17su8b0l/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 GSPD's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/cnw6rr26) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/cnw6rr26/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/gspd')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/gspd")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/gspd")
+```
+
+## 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": 1.6143786907196045, "eval_runtime": 6.648, "eval_samples_per_second": 22.563, "eval_steps_per_second": 2.858, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:903a60b019c3189ea2401d825a51588abe0295c21127eadc7f170f86b4711695
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf9330ebc61aeb2214f532e874e79d806f5773424f220a2a22e25116ae7d7ab
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:238219c7329b0b10459c22d9cd9fd9efb44970d69676335af067af5088ae373d
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1faa9800090f58192e975d9de4af52a7d1d95073c9339bf79e7455df2e035748
+size 14567

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1c2f47e2da491a315f90603f1d3a2627d77a6f03326673b420719eb45024ca9
+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 +1,144 @@
+{
+  "best_metric": 1.6143786907196045,
+  "best_model_checkpoint": "output/gspd/checkpoint-104",
+  "epoch": 1.0,
+  "global_step": 104,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00013641901727743684,
+      "loss": 2.3995,
+      "step": 5
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00013409385144248624,
+      "loss": 2.0772,
+      "step": 10
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00013027744460430822,
+      "loss": 1.9236,
+      "step": 15
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00012505669320030482,
+      "loss": 1.9836,
+      "step": 20
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00011855046943587908,
+      "loss": 1.876,
+      "step": 25
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00011090691466231807,
+      "loss": 1.9239,
+      "step": 30
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00010230006632035399,
+      "loss": 1.8628,
+      "step": 35
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.292589525111794e-05,
+      "loss": 1.6981,
+      "step": 40
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.299784360164853e-05,
+      "loss": 1.7632,
+      "step": 45
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.274196492316882e-05,
+      "loss": 1.8217,
+      "step": 50
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 6.239177711808685e-05,
+      "loss": 1.7681,
+      "step": 55
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 5.218294542987356e-05,
+      "loss": 1.7394,
+      "step": 60
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.2347916539754844e-05,
+      "loss": 1.8022,
+      "step": 65
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.311062594741274e-05,
+      "loss": 1.7416,
+      "step": 70
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.4681399144273327e-05,
+      "loss": 1.7103,
+      "step": 75
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.725216267546246e-05,
+      "loss": 1.7463,
+      "step": 80
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.0992074130600507e-05,
+      "loss": 1.6627,
+      "step": 85
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 6.043670564942622e-06,
+      "loss": 1.7961,
+      "step": 90
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.519623048140383e-06,
+      "loss": 1.7855,
+      "step": 95
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 5.001712368734975e-07,
+      "loss": 1.7266,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.6143786907196045,
+      "eval_runtime": 6.5105,
+      "eval_samples_per_second": 23.04,
+      "eval_steps_per_second": 2.918,
+      "step": 104
+    }
+  ],
+  "max_steps": 104,
+  "num_train_epochs": 1,
+  "total_flos": 108566839296000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87567da31bf0b1dfd45bb9ff251c20e21f066cdbbeca02722787462d643334e0
+size 2671