huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/max-korzh
+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/a1486b5b6f28eeec202b55e983e464c5.567x567x1.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">Макс Корж (Max Korzh)</div>
+    <a href="https://genius.com/artists/max-korzh">
+    	<div style="text-align: center; font-size: 14px;">@max-korzh</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 Макс Корж (Max Korzh).
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/max-korzh).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/max-korzh")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2lupo5gy/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 Макс Корж (Max Korzh)'s lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1pm64gaa) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1pm64gaa/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/max-korzh')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/max-korzh")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/max-korzh")
+```
+
+## 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": "4.10.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 1.8468588590621948, "eval_runtime": 4.2851, "eval_samples_per_second": 21.936, "eval_steps_per_second": 2.8, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e19ef419f6662fcd6d0e140e88c240407065e782a85e6f4ca91fe9a0ec4a8186
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7857b507355d1c865c2ffff697fe4079cc00459d1e66c02e82627787272d3db4
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aba2150545cba0dc299c10fdafa0cb4ec9f35d6c057643ec00bbbefa7d19923e
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb2cfcd172db8d520442e469438e46a8c0f7deb23577bc1c5a2fbf8cc3dea470
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8250a5b2245967ba67d3befe35c6f8287cf95e55bfd78f4174de3304afdd1fa
+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 +1,102 @@
+{
+  "best_metric": 1.8468588590621948,
+  "best_model_checkpoint": "output/max-korzh/checkpoint-66",
+  "epoch": 1.0,
+  "global_step": 66,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00013526627358699495,
+      "loss": 2.4173,
+      "step": 5
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00012957411177772776,
+      "loss": 2.2555,
+      "step": 10
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00012044442080070213,
+      "loss": 2.0536,
+      "step": 15
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0001083919039965842,
+      "loss": 2.0403,
+      "step": 20
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 9.409604445829847e-05,
+      "loss": 1.9983,
+      "step": 25
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 7.836279790554737e-05,
+      "loss": 1.9702,
+      "step": 30
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 6.207915542933309e-05,
+      "loss": 1.9274,
+      "step": 35
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.616313771642488e-05,
+      "loss": 1.9929,
+      "step": 40
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.151203992254603e-05,
+      "loss": 1.927,
+      "step": 45
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.8951844985992186e-05,
+      "loss": 1.9614,
+      "step": 50
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.190657300387505e-06,
+      "loss": 1.8335,
+      "step": 55
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.778782010045488e-06,
+      "loss": 1.8942,
+      "step": 60
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 7.770053204565375e-08,
+      "loss": 1.8146,
+      "step": 65
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.8468588590621948,
+      "eval_runtime": 4.2001,
+      "eval_samples_per_second": 22.381,
+      "eval_steps_per_second": 2.857,
+      "step": 66
+    }
+  ],
+  "max_steps": 66,
+  "num_train_epochs": 1,
+  "total_flos": 68458512384000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a5897b7c896836605065084f094d9fc3837ef2caf81e230c000530bc5ad382
+size 2671