huggingartists

README.md

@@ -0,0 +1,95 @@
+---
+language: en
+datasets:
+- huggingartists/morgenshtern
+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/22e752c5e4e7e4d2e8488babffb33bbf.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">MORGENSHTERN</div>
+    <a href="https://genius.com/artists/morgenshtern">
+    	<div style="text-align: center; font-size: 14px;">@morgenshtern</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 MORGENSHTERN.
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/morgenshtern).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/morgenshtern")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3q6pnb0j/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 MORGENSHTERN's lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2ury2mhk) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2ury2mhk/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/morgenshtern')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/morgenshtern")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/morgenshtern")
+```
+
+## 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)
+
+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": "4.9.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31606b5df45658b03ce97110b2fb5cd44b16f8c126a0aeca7a01cf0645b9696f
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1d282a1d71170062ecdb062d5c638852f43c3cd839ff61cacc44240716c313
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7be973f06905cedc248ba31c9027bfb7bed7f5330cc8eea151a16663cb260a5f
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1a77f16b5380cb9f8dfa41c789f6f7b0d5f10d7040476401f9a011e850af2a4
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc8c181f3eeffc22bed5df763ebe76f1c0ce2ad567f243d6703ceaa6e371773
+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 +1,176 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 102,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00013638815138477438,
+      "loss": 2.534,
+      "step": 5
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00013397182122930294,
+      "loss": 2.1207,
+      "step": 10
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0001300082017869573,
+      "loss": 1.9437,
+      "step": 15
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00012459110818763681,
+      "loss": 2.0463,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.9048744440078735,
+      "eval_runtime": 2.5437,
+      "eval_samples_per_second": 44.03,
+      "eval_steps_per_second": 5.504,
+      "step": 20
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00011784875792222071,
+      "loss": 1.953,
+      "step": 25
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.000109940736055617,
+      "loss": 2.0751,
+      "step": 30
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0001010542179989503,
+      "loss": 1.9436,
+      "step": 35
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.139953924430466e-05,
+      "loss": 1.8745,
+      "step": 40
+    },
+    {
+      "epoch": 0.39,
+      "eval_loss": 1.7966899871826172,
+      "eval_runtime": 2.5987,
+      "eval_samples_per_second": 43.099,
+      "eval_steps_per_second": 5.387,
+      "step": 40
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.120521692221673e-05,
+      "loss": 1.8989,
+      "step": 45
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 7.071254101695329e-05,
+      "loss": 1.8346,
+      "step": 50
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 6.016986326040062e-05,
+      "loss": 1.8576,
+      "step": 55
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.982671888105512e-05,
+      "loss": 1.8876,
+      "step": 60
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 1.760327935218811,
+      "eval_runtime": 2.6932,
+      "eval_samples_per_second": 41.586,
+      "eval_steps_per_second": 5.198,
+      "step": 60
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.992792034076668e-05,
+      "loss": 1.7386,
+      "step": 65
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.0707762854909304e-05,
+      "loss": 1.9309,
+      "step": 70
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.2384478845846175e-05,
+      "loss": 1.6283,
+      "step": 75
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.5155072587539005e-05,
+      "loss": 1.9742,
+      "step": 80
+    },
+    {
+      "epoch": 0.78,
+      "eval_loss": 1.7276561260223389,
+      "eval_runtime": 2.6936,
+      "eval_samples_per_second": 41.581,
+      "eval_steps_per_second": 5.198,
+      "step": 80
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.190657300387505e-06,
+      "loss": 1.8267,
+      "step": 85
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.6324050628611986e-06,
+      "loss": 1.7887,
+      "step": 90
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.5882054016913933e-06,
+      "loss": 1.8381,
+      "step": 95
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.3011164863877445e-07,
+      "loss": 1.8954,
+      "step": 100
+    },
+    {
+      "epoch": 0.98,
+      "eval_loss": 1.7208999395370483,
+      "eval_runtime": 2.7574,
+      "eval_samples_per_second": 40.618,
+      "eval_steps_per_second": 5.077,
+      "step": 100
+    }
+  ],
+  "max_steps": 102,
+  "num_train_epochs": 1,
+  "total_flos": 106345857024000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f915a601b161294d09f0795c26c67c9dddff75c8768bf2451d5a65f6c1dd3a2
+size 2671