huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/bones
+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/564dc935d7c601860b155b359d8ddf9d.1000x1000x1.png&#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">BONES</div>
+    <a href="https://genius.com/artists/bones">
+    	<div style="text-align: center; font-size: 14px;">@bones</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 BONES.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/bones).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/bones")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/26h7sojw/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 BONES's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1yr1mvc2) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1yr1mvc2/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/bones')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/bones")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/bones")
+```
+
+## 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 +1,40 @@
+{
+  "_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,
+  "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": "4.11.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 3.516153573989868, "eval_runtime": 9.1233, "eval_samples_per_second": 22.141, "eval_steps_per_second": 2.85, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c146337b2b4d723f9b1a29771e7afdc0fa3f1f1342f2f4a706eed9ae1650a841
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a804f5ac6f1ed67c1037d889a362a20aec52eb0cdfb6d28fe02ca0b23e9f6aec
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66cef7f28919b6cff8829e7d3bd04f4098aee3c6d27e26eeec13955081f43504
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99966cfb2c88711419cbaac8b6daf330700497742a0d28a569bfa56c42a3fa22
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874f414e996bed5c01ac5b2a3b90399694a3bb1b56ce1bf829358b7185235dd2
+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 +1,180 @@
+{
+  "best_metric": 3.516153573989868,
+  "best_model_checkpoint": "output/bones/checkpoint-131",
+  "epoch": 1.0,
+  "global_step": 131,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00013670742670262692,
+      "loss": 4.0743,
+      "step": 5
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00013523678052634687,
+      "loss": 4.0532,
+      "step": 10
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00013280918103490095,
+      "loss": 3.8244,
+      "step": 15
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00012945949034742042,
+      "loss": 3.8818,
+      "step": 20
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00012523581249268407,
+      "loss": 3.7574,
+      "step": 25
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00012019880259978666,
+      "loss": 3.8753,
+      "step": 30
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011442079584574986,
+      "loss": 3.6832,
+      "step": 35
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00010798476866903087,
+      "loss": 3.764,
+      "step": 40
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00010098314716666811,
+      "loss": 3.7562,
+      "step": 45
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.351647978736063e-05,
+      "loss": 3.8048,
+      "step": 50
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.5691993381587e-05,
+      "loss": 3.8516,
+      "step": 55
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 7.762205334494898e-05,
+      "loss": 3.7629,
+      "step": 60
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 6.942254996821776e-05,
+      "loss": 3.7416,
+      "step": 65
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 6.121123416728538e-05,
+      "loss": 3.5754,
+      "step": 70
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.310602649316754e-05,
+      "loss": 3.625,
+      "step": 75
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.5223323705920566e-05,
+      "loss": 3.5876,
+      "step": 80
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.7676327231320786e-05,
+      "loss": 3.5927,
+      "step": 85
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.0573417504900444e-05,
+      "loss": 3.4549,
+      "step": 90
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 2.401659754895943e-05,
+      "loss": 3.8261,
+      "step": 95
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.8100028133934438e-05,
+      "loss": 3.6442,
+      "step": 100
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.2908675560288951e-05,
+      "loss": 3.7345,
+      "step": 105
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.517091479772992e-06,
+      "loss": 3.4828,
+      "step": 110
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.988342278719811e-06,
+      "loss": 3.5471,
+      "step": 115
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.3731033982246404e-06,
+      "loss": 3.5867,
+      "step": 120
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.089315974356758e-07,
+      "loss": 3.4037,
+      "step": 125
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.9725610793441152e-08,
+      "loss": 3.6132,
+      "step": 130
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.516153573989868,
+      "eval_runtime": 9.0194,
+      "eval_samples_per_second": 22.396,
+      "eval_steps_per_second": 2.883,
+      "step": 131
+    }
+  ],
+  "max_steps": 131,
+  "num_train_epochs": 1,
+  "total_flos": 136133148672000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e18bd18597806a84e61c11d161145705196f624e949e9d9a4749ae99181a2a2
+size 2863