huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/elton-john
+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/ec76d346c4c8b057169194c1781021fd.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">Elton John</div>
+    <a href="https://genius.com/artists/elton-john">
+    	<div style="text-align: center; font-size: 14px;">@elton-john</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 Elton John.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/elton-john).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/elton-john")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/4l9f8jif/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 Elton John's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/9glyfrcq) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/9glyfrcq/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/elton-john')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/elton-john")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/elton-john")
+```
+
+## 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": "4.10.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 3.0393269062042236, "eval_runtime": 9.0147, "eval_samples_per_second": 22.852, "eval_steps_per_second": 2.884, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80c5335361f4b5826d3c8dcbf64dc173264028aa9a8ed9f51f27f3025014f6dc
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb57694a5fd1f450d99621dea90750bd8c71a315ae39a7ac81bf32c09f7c1c07
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc049c7460156279f44ea714b704592cadbf8d4a7d08b8b2a7e4e581447462f9
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dcaf38b2ba417b9e7c855abc82748c9660bcba4c77392d9424bf18c41d62c2a
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb71b8d9941063c635df32e061d21e647151549cf90fc9dd70cfed3b990a34f9
+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 +1,216 @@
+{
+  "best_metric": 3.0393269062042236,
+  "best_model_checkpoint": "output/elton-john/checkpoint-161",
+  "epoch": 1.0,
+  "global_step": 161,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001368737597109298,
+      "loss": 3.2318,
+      "step": 5
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001358981418386525,
+      "loss": 3.49,
+      "step": 10
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00013428242585420812,
+      "loss": 3.4363,
+      "step": 15
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00013204197944418041,
+      "loss": 3.3779,
+      "step": 20
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00012919811234281,
+      "loss": 3.5486,
+      "step": 25
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00012577787364704225,
+      "loss": 3.156,
+      "step": 30
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001218137945423232,
+      "loss": 3.4707,
+      "step": 35
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011734357888617527,
+      "loss": 3.2883,
+      "step": 40
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00011240974459253048,
+      "loss": 3.2899,
+      "step": 45
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00010705921922774988,
+      "loss": 3.0576,
+      "step": 50
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00010134289366476881,
+      "loss": 2.9129,
+      "step": 55
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.531513804073266e-05,
+      "loss": 3.1296,
+      "step": 60
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.903328462203299e-05,
+      "loss": 3.3835,
+      "step": 65
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.255708249541069e-05,
+      "loss": 3.0019,
+      "step": 70
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 7.594812927176565e-05,
+      "loss": 3.0587,
+      "step": 75
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 6.926928520795311e-05,
+      "loss": 3.2402,
+      "step": 80
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 6.258407531907605e-05,
+      "loss": 3.0662,
+      "step": 85
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5.5956085168010344e-05,
+      "loss": 3.0189,
+      "step": 90
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.9448356079036955e-05,
+      "loss": 3.3076,
+      "step": 95
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.312278552793369e-05,
+      "loss": 3.1185,
+      "step": 100
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.703953841164296e-05,
+      "loss": 2.9762,
+      "step": 105
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.125647479715328e-05,
+      "loss": 3.1833,
+      "step": 110
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.5828599592490882e-05,
+      "loss": 3.0905,
+      "step": 115
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.080753937420995e-05,
+      "loss": 3.0524,
+      "step": 120
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.624105134747227e-05,
+      "loss": 2.931,
+      "step": 125
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.2172569109183958e-05,
+      "loss": 3.0424,
+      "step": 130
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.640789534607252e-06,
+      "loss": 3.3083,
+      "step": 135
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5.679304716725937e-06,
+      "loss": 3.3548,
+      "step": 140
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.3162824591277986e-06,
+      "loss": 3.1647,
+      "step": 145
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.574198361357997e-06,
+      "loss": 3.0154,
+      "step": 150
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.696220449804098e-07,
+      "loss": 3.0273,
+      "step": 155
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.3059553632214649e-08,
+      "loss": 3.1636,
+      "step": 160
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.0393269062042236,
+      "eval_runtime": 8.8221,
+      "eval_samples_per_second": 23.351,
+      "eval_steps_per_second": 2.947,
+      "step": 161
+    }
+  ],
+  "max_steps": 161,
+  "num_train_epochs": 1,
+  "total_flos": 167880130560000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c9d72369b89deab6316d05e8deee4071405452ec742851b48a28764b370d00
+size 2671