huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/kurt-cobain
+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/8c394f5b79ddaa5349e8a4cc10c1ab48.400x400x1.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">Kurt Cobain</div>
+    <a href="https://genius.com/artists/kurt-cobain">
+    	<div style="text-align: center; font-size: 14px;">@kurt-cobain</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 Kurt Cobain.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/kurt-cobain).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/kurt-cobain")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1whd1v3b/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 Kurt Cobain's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3nzvvuyl) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3nzvvuyl/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/kurt-cobain')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/kurt-cobain")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/kurt-cobain")
+```
+
+## 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": "4.11.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 2.059675931930542, "eval_runtime": 3.7661, "eval_samples_per_second": 21.773, "eval_steps_per_second": 2.921, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cfb2fb84e95c1f4166fbc68132aab67b3e2d43bb335046b2db6d09528a0fff9
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbc63b097ef5c6b54b802015cc1fd80b5d7fb752db3f09423f2231b2fd9bf470
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbd5a79c6d6f4397e979deb5ed837e7a31a9444a389f1e4b7d9b629e59679130
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3669fa98bb5c4efd6c0df7cdf49d6ef6463037ace488e6ccbace1eb61273d86
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea254c15c4fd5cb1f8de5c78442f725e8358618f09aaa6308f4d0adddbd45447
+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 +1,96 @@
+{
+  "best_metric": 2.059675931930542,
+  "best_model_checkpoint": "output/kurt-cobain/checkpoint-63",
+  "epoch": 1.0,
+  "global_step": 63,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00013507870183531476,
+      "loss": 3.0032,
+      "step": 5
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00012884599993319768,
+      "loss": 2.5844,
+      "step": 10
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00011888735840752609,
+      "loss": 2.5435,
+      "step": 15
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001058186737011911,
+      "loss": 2.4834,
+      "step": 20
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.044818420726556e-05,
+      "loss": 2.4343,
+      "step": 25
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.372648442002871e-05,
+      "loss": 2.7558,
+      "step": 30
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5.668773501204858e-05,
+      "loss": 2.5089,
+      "step": 35
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.0385704725240065e-05,
+      "loss": 2.4147,
+      "step": 40
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.5828599592490882e-05,
+      "loss": 2.123,
+      "step": 45
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.3916710004507539e-05,
+      "loss": 2.2562,
+      "step": 50
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5.38673186569003e-06,
+      "loss": 2.4784,
+      "step": 55
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.662053209561833e-07,
+      "loss": 2.5457,
+      "step": 60
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.059675931930542,
+      "eval_runtime": 3.6409,
+      "eval_samples_per_second": 22.522,
+      "eval_steps_per_second": 3.021,
+      "step": 63
+    }
+  ],
+  "max_steps": 63,
+  "num_train_epochs": 1,
+  "total_flos": 64931069952000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:827966f81c0e881fb54a56100eb0000ea908c70ca55363e9cba79025ffe95eea
+size 2863