huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/lil-nas-x
+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/f50e1ac333da1f744f98eec38e44dd29.640x640x1.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">Lil Nas X</div>
+    <a href="https://genius.com/artists/lil-nas-x">
+    	<div style="text-align: center; font-size: 14px;">@lil-nas-x</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 Lil Nas X.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/lil-nas-x).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/lil-nas-x")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/i3cxi0c3/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 Lil Nas X's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1qrt007n) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1qrt007n/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/lil-nas-x')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/lil-nas-x")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/lil-nas-x")
+```
+
+## 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": 2.9424936771392822, "eval_runtime": 1.2434, "eval_samples_per_second": 20.106, "eval_steps_per_second": 3.217, "epoch": 10.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20f0207e6068480b12b0f0a1e986ad0b838ed6813a6cb3025608abce843f64a6
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca5db0a9b829f45ea81c1628183f47350c94e9b0ca90c2c7284c95ad41aeee0
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97c65e91bdea4a97855ae617ec185512034c6de6b74b727c5d47b4834600048e
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dff0838f6c4266c52ad3f733c18288237e78c922be8b97cbee6dca8f0e06b0d4
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:858b0150f63e516bfdd54df0bdcc3e1de87c6a580f8d9790a43f52a335f62cca
+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 +1,196 @@
+{
+  "best_metric": 2.9424936771392822,
+  "best_model_checkpoint": "output/lil-nas-x/checkpoint-114",
+  "epoch": 6.0,
+  "global_step": 114,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00011506151581352585,
+      "loss": 3.7671,
+      "step": 5
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 6.293505690059801e-05,
+      "loss": 3.4851,
+      "step": 10
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.4464961055407408e-05,
+      "loss": 3.237,
+      "step": 15
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.2925262451171875,
+      "eval_runtime": 1.1351,
+      "eval_samples_per_second": 22.025,
+      "eval_steps_per_second": 3.524,
+      "step": 19
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.35614586573241e-07,
+      "loss": 3.3051,
+      "step": 20
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 3.1079356352801514e-05,
+      "loss": 3.2407,
+      "step": 25
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.54403044178588e-05,
+      "loss": 3.0887,
+      "step": 30
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00012893189933276512,
+      "loss": 3.1123,
+      "step": 35
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.1396188735961914,
+      "eval_runtime": 1.1208,
+      "eval_samples_per_second": 22.306,
+      "eval_steps_per_second": 3.569,
+      "step": 38
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.00013348306278066356,
+      "loss": 2.9306,
+      "step": 40
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 9.615630613119375e-05,
+      "loss": 2.8064,
+      "step": 45
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 4.1043693868806304e-05,
+      "loss": 2.7433,
+      "step": 50
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 3.7169372193364486e-06,
+      "loss": 2.7272,
+      "step": 55
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.06833553314209,
+      "eval_runtime": 1.1266,
+      "eval_samples_per_second": 22.191,
+      "eval_steps_per_second": 3.551,
+      "step": 57
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 8.268100667234827e-06,
+      "loss": 2.7817,
+      "step": 60
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 5.175969558214116e-05,
+      "loss": 2.5931,
+      "step": 65
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 0.0001061206436471984,
+      "loss": 2.6951,
+      "step": 70
+    },
+    {
+      "epoch": 3.95,
+      "learning_rate": 0.00013626438541342674,
+      "loss": 2.4538,
+      "step": 75
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.0064802169799805,
+      "eval_runtime": 1.1266,
+      "eval_samples_per_second": 22.191,
+      "eval_steps_per_second": 3.551,
+      "step": 76
+    },
+    {
+      "epoch": 4.21,
+      "learning_rate": 0.00012273503894459262,
+      "loss": 2.3701,
+      "step": 80
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 7.426494309940199e-05,
+      "loss": 2.2971,
+      "step": 85
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 2.2138484186474223e-05,
+      "loss": 2.4709,
+      "step": 90
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 2.1501,
+      "step": 95
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.979142665863037,
+      "eval_runtime": 1.1215,
+      "eval_samples_per_second": 22.292,
+      "eval_steps_per_second": 3.567,
+      "step": 95
+    },
+    {
+      "epoch": 5.26,
+      "learning_rate": 2.2138484186474162e-05,
+      "loss": 2.1304,
+      "step": 100
+    },
+    {
+      "epoch": 5.53,
+      "learning_rate": 7.426494309940202e-05,
+      "loss": 2.3152,
+      "step": 105
+    },
+    {
+      "epoch": 5.79,
+      "learning_rate": 0.00012273503894459265,
+      "loss": 2.3139,
+      "step": 110
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.9424936771392822,
+      "eval_runtime": 1.1322,
+      "eval_samples_per_second": 22.081,
+      "eval_steps_per_second": 3.533,
+      "step": 114
+    }
+  ],
+  "max_steps": 190,
+  "num_train_epochs": 10,
+  "total_flos": 116013662208000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:567145a7fe28355135b0476020151a6d4f254152553e83298e8d9a53a3d93243
+size 2671