huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/mayot
+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/1d4b4adcdf1f58e1899ee5557375ef7c.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">MAYOT</div>
+    <a href="https://genius.com/artists/mayot">
+    	<div style="text-align: center; font-size: 14px;">@mayot</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 MAYOT.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/mayot).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/mayot")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/lf4wcx85/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 MAYOT's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1uulibm2) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1uulibm2/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/mayot')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/mayot")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/mayot")
+```
+
+## 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": "4.11.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 1.9315155744552612, "eval_runtime": 8.8038, "eval_samples_per_second": 21.241, "eval_steps_per_second": 2.726, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ea887f2e75b426c00c3d6bd0d13a1b439da43e32d8bac3ed6c5be4d868b6b6
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ca34a4170ce51290fd95c5ac59fd49dba84988be73c98a438e3983caae03313
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6553883a5f0e87971ebb160575a5d83c53e1732fc50ad64c0de0d1aea6ac8683
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:998b7e4f211da1272e8bac8c21cce58bf728ff4661fb28aa0a976fb3b885b197
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b0d0933f93d27b57495fddadcfbb827f68914ac01774cd2c666048ba2574c1
+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 +1,198 @@
+{
+  "best_metric": 1.9315155744552612,
+  "best_model_checkpoint": "output/mayot/checkpoint-147",
+  "epoch": 1.0,
+  "global_step": 147,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00013680872155869608,
+      "loss": 2.7218,
+      "step": 5
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00013563934975719332,
+      "loss": 2.4506,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00013370522424493186,
+      "loss": 2.3233,
+      "step": 15
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0001310284086258687,
+      "loss": 2.2628,
+      "step": 20
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001276394387671491,
+      "loss": 2.169,
+      "step": 25
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00012357697446014183,
+      "loss": 2.1897,
+      "step": 30
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00011888735840752609,
+      "loss": 2.1417,
+      "step": 35
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00011362408756730135,
+      "loss": 2.091,
+      "step": 40
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00010784720288438084,
+      "loss": 2.0851,
+      "step": 45
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00010162260437142711,
+      "loss": 2.1085,
+      "step": 50
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.502129935216876e-05,
+      "loss": 2.0363,
+      "step": 55
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.811859244288883e-05,
+      "loss": 2.0587,
+      "step": 60
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.099322651239897e-05,
+      "loss": 2.0127,
+      "step": 65
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.372648442002871e-05,
+      "loss": 1.9725,
+      "step": 70
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 6.640126177858445e-05,
+      "loss": 1.9979,
+      "step": 75
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 5.910112131976733e-05,
+      "loss": 2.0089,
+      "step": 80
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 5.190933964940903e-05,
+      "loss": 1.9777,
+      "step": 85
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.4907957266698305e-05,
+      "loss": 2.0007,
+      "step": 90
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.8176842684337195e-05,
+      "loss": 2.0053,
+      "step": 95
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.179278132570837e-05,
+      "loss": 1.9833,
+      "step": 100
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.5828599592490882e-05,
+      "loss": 1.983,
+      "step": 105
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.035233409495375e-05,
+      "loss": 1.9408,
+      "step": 110
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.5426455521961213e-05,
+      "loss": 1.9111,
+      "step": 115
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.1107156004419736e-05,
+      "loss": 1.9171,
+      "step": 120
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.4437081015931425e-06,
+      "loss": 1.898,
+      "step": 125
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.477902722671392e-06,
+      "loss": 1.9822,
+      "step": 130
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.24357239552258e-06,
+      "loss": 1.8845,
+      "step": 135
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.662053209561833e-07,
+      "loss": 1.9681,
+      "step": 140
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.26546151870577e-08,
+      "loss": 1.9478,
+      "step": 145
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.9315155744552612,
+      "eval_runtime": 8.7552,
+      "eval_samples_per_second": 21.359,
+      "eval_steps_per_second": 2.741,
+      "step": 147
+    }
+  ],
+  "max_steps": 147,
+  "num_train_epochs": 1,
+  "total_flos": 152855838720000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c81e2ba72a3c35aaac410ea4726dde6932ce249ed404d43e7ca4390fcaa1b27
+size 2863