huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/ariana-grande
+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/d36a47955ac0ddb12748c5e7c2bd4b4b.640x640x1.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">Ariana Grande</div>
+    <a href="https://genius.com/artists/ariana-grande">
+    	<div style="text-align: center; font-size: 14px;">@ariana-grande</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 Ariana Grande.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/ariana-grande).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/ariana-grande")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2nfg7v7i/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 Ariana Grande's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3u3sn1bx) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3u3sn1bx/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/ariana-grande')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/ariana-grande")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/ariana-grande")
+```
+
+## 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": "4.10.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 2.574702262878418, "eval_runtime": 7.3523, "eval_samples_per_second": 22.17, "eval_steps_per_second": 2.856, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9db96b149feef8de1be0f238d588fc2add151d8ae820af713e4c3dade581220
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80bd6e22b1b81043e243056874eca15b34dafa8461d1fa3965f5a2c92a46c72c
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e999f1a8834518f8db78e93315cb828277f2d6328a6640eb59839ff6a19bfe4
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e1a4ac4390fe2e0994c25ed32a9e3f7ae71562cbab84951364fc94bb292239
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:320f3442b58470d7f228e7f3b3cbe052aaaeb78c1108e96f25db8d996fb76cc7
+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 +1,156 @@
+{
+  "best_metric": 2.574702262878418,
+  "best_model_checkpoint": "output/ariana-grande/checkpoint-112",
+  "epoch": 1.0,
+  "global_step": 112,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00013652642519808018,
+      "loss": 3.1432,
+      "step": 5
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00013451892828543385,
+      "loss": 3.0156,
+      "step": 10
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00013121693198320648,
+      "loss": 3.0148,
+      "step": 15
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00012668528006706028,
+      "loss": 2.7633,
+      "step": 20
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00012101296398136228,
+      "loss": 2.7487,
+      "step": 25
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011431137524750748,
+      "loss": 2.8109,
+      "step": 30
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00010671211798514472,
+      "loss": 2.7869,
+      "step": 35
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.836442450346448e-05,
+      "loss": 2.7909,
+      "step": 40
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.943222471451957e-05,
+      "loss": 2.7036,
+      "step": 45
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 8.009092691870492e-05,
+      "loss": 2.6624,
+      "step": 50
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.052397318052461e-05,
+      "loss": 2.4311,
+      "step": 55
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 6.0919236939313083e-05,
+      "loss": 2.8251,
+      "step": 60
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 5.146533359772823e-05,
+      "loss": 2.6649,
+      "step": 65
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.2347916539754844e-05,
+      "loss": 2.6419,
+      "step": 70
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.3746031316088095e-05,
+      "loss": 2.6433,
+      "step": 75
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.5828599592490882e-05,
+      "loss": 2.9171,
+      "step": 80
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.8751101908465757e-05,
+      "loss": 2.5503,
+      "step": 85
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.2652524389394753e-05,
+      "loss": 2.6036,
+      "step": 90
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.65262937184937e-06,
+      "loss": 2.6237,
+      "step": 95
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.849603540845984e-06,
+      "loss": 2.4549,
+      "step": 100
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.3181297643383925e-06,
+      "loss": 2.6479,
+      "step": 105
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0792048977778093e-07,
+      "loss": 2.6504,
+      "step": 110
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.574702262878418,
+      "eval_runtime": 7.2482,
+      "eval_samples_per_second": 22.488,
+      "eval_steps_per_second": 2.897,
+      "step": 112
+    }
+  ],
+  "max_steps": 112,
+  "num_train_epochs": 1,
+  "total_flos": 117058830336000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30b4053e8beea2a1075e863c9fc3588d52f816ed72d11f8c6e6569a178071760
+size 2671