huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/miyagi
+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/10795217955d95e2543993f8e83fe5c8.960x960x1.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">MiyaGi</div>
+    <a href="https://genius.com/artists/miyagi">
+    	<div style="text-align: center; font-size: 14px;">@miyagi</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 MiyaGi.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/miyagi).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/miyagi")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/33axhvp7/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 MiyaGi's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/560sm315) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/560sm315/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/miyagi')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/miyagi")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/miyagi")
+```
+
+## 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": 1.9889769554138184, "eval_runtime": 8.2714, "eval_samples_per_second": 20.432, "eval_steps_per_second": 2.66, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44ffebc9bed4a9a2d516e6fe2d55e2a84e9108938d76c1bf82c7bc9e87e0eeb3
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83e6a184300a4da7de3a0ae9368b17270bf1f0c60cb18344e094885437d4ded9
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7f820636f754a7aa82e3715071861e73590860152f7a49ca45aba55fe00b410
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a0991fc954782244b3d68425edce12ebcd44630d9d81754c57a010a17f834cf
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e90c182f2545f26454b003c854f4df0419ef205b274b2e4a9121c08f80493a77
+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 +1,168 @@
+{
+  "best_metric": 1.9889769554138184,
+  "best_model_checkpoint": "output/miyagi/checkpoint-120",
+  "epoch": 1.0,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0001366131174902434,
+      "loss": 2.5015,
+      "step": 5
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00013486251168343008,
+      "loss": 2.2103,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00013197813593027427,
+      "loss": 2.3049,
+      "step": 15
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001280093426996125,
+      "loss": 2.2693,
+      "step": 20
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00012302403914397873,
+      "loss": 2.0156,
+      "step": 25
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011710752518939715,
+      "loss": 2.1099,
+      "step": 30
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00011036103402999824,
+      "loss": 2.0083,
+      "step": 35
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00010290000000000001,
+      "loss": 2.046,
+      "step": 40
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.485208346024516e-05,
+      "loss": 1.8954,
+      "step": 45
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.635498649403293e-05,
+      "loss": 2.2916,
+      "step": 50
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 7.755409678629555e-05,
+      "loss": 1.9975,
+      "step": 55
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 6.86e-05,
+      "loss": 2.045,
+      "step": 60
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 5.964590321370448e-05,
+      "loss": 1.9664,
+      "step": 65
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 5.084501350596707e-05,
+      "loss": 1.8793,
+      "step": 70
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.2347916539754844e-05,
+      "loss": 2.014,
+      "step": 75
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 3.4300000000000014e-05,
+      "loss": 1.9299,
+      "step": 80
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 2.6838965970001764e-05,
+      "loss": 1.9819,
+      "step": 85
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.0092474810602843e-05,
+      "loss": 2.051,
+      "step": 90
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.4175960856021275e-05,
+      "loss": 1.9671,
+      "step": 95
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.190657300387505e-06,
+      "loss": 1.8122,
+      "step": 100
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 5.22186406972573e-06,
+      "loss": 1.8996,
+      "step": 105
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.3374883165699215e-06,
+      "loss": 2.0356,
+      "step": 110
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 5.868825097566078e-07,
+      "loss": 1.8357,
+      "step": 115
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 2.0548,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.9889769554138184,
+      "eval_runtime": 8.2484,
+      "eval_samples_per_second": 20.489,
+      "eval_steps_per_second": 2.667,
+      "step": 120
+    }
+  ],
+  "max_steps": 120,
+  "num_train_epochs": 1,
+  "total_flos": 125158883328000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16a13486ddcf5f6cc2d8ddfca1f9d43d401ea752c8f92491f44c7ffa413e82c1
+size 2671