huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/travis-scott
+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/5d19fecdb3828ca9ec89dda588e2eb7d.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">Travis Scott</div>
+    <a href="https://genius.com/artists/travis-scott">
+    	<div style="text-align: center; font-size: 14px;">@travis-scott</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 Travis Scott.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/travis-scott).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/travis-scott")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1ezlbvd0/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 Travis Scott's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2w91gglb) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2w91gglb/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/travis-scott')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/travis-scott")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/travis-scott")
+```
+
+## 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": 3.3389594554901123, "eval_runtime": 11.9214, "eval_samples_per_second": 20.971, "eval_steps_per_second": 2.684, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cc037406becdbe41ebed11df1d131b93a2dcc027c71a1df2bc3ec2f0a493741
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bd2ab29016637790d4dacb168e082d34e4686870fbd538a8fac2d1b940438f6
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff2081d607df10f34f6f41851e8dfee4e8c116863447af9ff75f79c577e9523
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c7292261f560fe6a0ac7b885ea22f426493f72d97784f3ce5a91d85561b201d
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe9f4d4debed71c7352db954e283fda16ca7e08b2048603ff07fc59b5a44f11
+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 +1,228 @@
+{
+  "best_metric": 3.3389594554901123,
+  "best_model_checkpoint": "output/travis-scott/checkpoint-174",
+  "epoch": 1.0,
+  "global_step": 174,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001369206553164936,
+      "loss": 3.9488,
+      "step": 5
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00013608489629373538,
+      "loss": 3.7969,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00013469952948681868,
+      "loss": 3.6955,
+      "step": 15
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00013277583754449623,
+      "loss": 3.6337,
+      "step": 20
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00013032948732148497,
+      "loss": 3.5633,
+      "step": 25
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001273804022850966,
+      "loss": 3.4878,
+      "step": 30
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001239526002553348,
+      "loss": 3.6424,
+      "step": 35
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0001200739977999292,
+      "loss": 3.5744,
+      "step": 40
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00011577618287734484,
+      "loss": 3.4553,
+      "step": 45
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0001110941575793986,
+      "loss": 3.5316,
+      "step": 50
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00010606605306862761,
+      "loss": 3.4538,
+      "step": 55
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00010073281903200561,
+      "loss": 3.2755,
+      "step": 60
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.513789018014557e-05,
+      "loss": 3.2518,
+      "step": 65
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.932683250807268e-05,
+      "loss": 3.4163,
+      "step": 70
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.334697219847626e-05,
+      "loss": 3.3031,
+      "step": 75
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 7.724701018971185e-05,
+      "loss": 3.2611,
+      "step": 80
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.107662554757363e-05,
+      "loss": 3.3722,
+      "step": 85
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 6.488607087104036e-05,
+      "loss": 3.3329,
+      "step": 90
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 5.872576302707542e-05,
+      "loss": 3.3299,
+      "step": 95
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 5.264587254760233e-05,
+      "loss": 3.3178,
+      "step": 100
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.6695915032671784e-05,
+      "loss": 3.4824,
+      "step": 105
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.092434788749914e-05,
+      "loss": 3.412,
+      "step": 110
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.537817567760932e-05,
+      "loss": 3.121,
+      "step": 115
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.0102567316140575e-05,
+      "loss": 3.3823,
+      "step": 120
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2.5140488200994943e-05,
+      "loss": 3.217,
+      "step": 125
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.0532350297768717e-05,
+      "loss": 3.2794,
+      "step": 130
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.6315683018244145e-05,
+      "loss": 3.232,
+      "step": 135
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.2524827574860022e-05,
+      "loss": 3.2429,
+      "step": 140
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.190657300387505e-06,
+      "loss": 3.2955,
+      "step": 145
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.340326210572357e-06,
+      "loss": 3.2237,
+      "step": 150
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.9970478574895515e-06,
+      "loss": 3.2312,
+      "step": 155
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.179906274664157e-06,
+      "loss": 3.3031,
+      "step": 160
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 9.037005536513067e-07,
+      "loss": 3.4051,
+      "step": 165
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.7882431786864473e-07,
+      "loss": 3.4258,
+      "step": 170
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.3389594554901123,
+      "eval_runtime": 11.911,
+      "eval_samples_per_second": 20.989,
+      "eval_steps_per_second": 2.687,
+      "step": 174
+    }
+  ],
+  "max_steps": 174,
+  "num_train_epochs": 1,
+  "total_flos": 181597962240000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:413ed46a56fc054505b1326b94de4f7aca8d80552d1e9a992708bae96916ac37
+size 2671