huggingartists

README.md

@@ -0,0 +1,97 @@
+---
+language: en
+datasets:
+- huggingartists/dzhizus
+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/a96a6042b4c0a4c0bdae647768c5e42b.668x668x1.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">Джизус (Dzhizus)</div>
+    <a href="https://genius.com/artists/dzhizus">
+    	<div style="text-align: center; font-size: 14px;">@dzhizus</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 Джизус (Dzhizus).
+
+Dataset is available [here](https://huggingface.co/datasets/huggingartists/dzhizus).
+And can be used with:
+
+```python
+from datasets import load_dataset
+
+dataset = load_dataset("huggingartists/dzhizus")
+```
+
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/35paacn1/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 Джизус (Dzhizus)'s lyrics.
+
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1ug3yebo) for full transparency and reproducibility.
+
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1ug3yebo/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/dzhizus')
+generator("I am", num_return_sequences=5)
+```
+
+Or with Transformers library:
+
+```python
+from transformers import AutoTokenizer, AutoModelWithLMHead
+  
+tokenizer = AutoTokenizer.from_pretrained("huggingartists/dzhizus")
+
+model = AutoModelWithLMHead.from_pretrained("huggingartists/dzhizus")
+```
+
+## 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": "4.11.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

evaluation.txt

@@ -0,0 +1 @@
+{"eval_loss": 1.6611980199813843, "eval_runtime": 6.9911, "eval_samples_per_second": 22.028, "eval_steps_per_second": 2.861, "epoch": 1.0}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6260f17b0af98176ba8e258b43b74a607ffd4faf39815755788fc599913dd6ee
+size 497764120

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfe39bea22c1d3eefe350aaabe064b006247c42f157006f0a0ade31ab4280264
+size 995603825

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ad49f066d9d27f59377df6400798e1c14ae95ff53502934ac8bab93831a145
+size 510403817

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74c89b6ef353fbe4c7bffcfd9cd3fcdb94c39f7302b65e7786b3efbc781a4626
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c154c3161badb2d53847e65fdbe518ccea4845a5cf5e5f636b328e86f8ea7692
+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 +1,150 @@
+{
+  "best_metric": 1.6611980199813843,
+  "best_model_checkpoint": "output/dzhizus/checkpoint-108",
+  "epoch": 1.0,
+  "global_step": 108,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00013647569640665277,
+      "loss": 2.4321,
+      "step": 5
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00013431808054484255,
+      "loss": 2.1139,
+      "step": 10
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0001307727141907142,
+      "loss": 1.9824,
+      "step": 15
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00012591446386292745,
+      "loss": 1.7208,
+      "step": 20
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00011984591988713233,
+      "loss": 1.6687,
+      "step": 25
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00011269523002449659,
+      "loss": 1.6941,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00010461339341095083,
+      "loss": 1.7329,
+      "step": 35
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.577107195028616e-05,
+      "loss": 1.7829,
+      "step": 40
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.635498649403293e-05,
+      "loss": 1.6329,
+      "step": 45
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 7.65639739089908e-05,
+      "loss": 1.5783,
+      "step": 50
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 6.660478829422256e-05,
+      "loss": 1.6391,
+      "step": 55
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 5.668773501204858e-05,
+      "loss": 1.6529,
+      "step": 60
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.702222972799932e-05,
+      "loss": 1.5268,
+      "step": 65
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.7812376238248296e-05,
+      "loss": 1.5841,
+      "step": 70
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 2.9252656466318256e-05,
+      "loss": 1.6704,
+      "step": 75
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 2.152382364220488e-05,
+      "loss": 1.5718,
+      "step": 80
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.4789085386517107e-05,
+      "loss": 1.5881,
+      "step": 85
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.190657300387505e-06,
+      "loss": 1.489,
+      "step": 90
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.846759838039973e-06,
+      "loss": 1.6933,
+      "step": 95
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.849121878224087e-06,
+      "loss": 1.7571,
+      "step": 100
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.610437109062556e-07,
+      "loss": 1.5787,
+      "step": 105
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.6611980199813843,
+      "eval_runtime": 6.9528,
+      "eval_samples_per_second": 22.149,
+      "eval_steps_per_second": 2.877,
+      "step": 108
+    }
+  ],
+  "max_steps": 108,
+  "num_train_epochs": 1,
+  "total_flos": 112878157824000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9424218f892a1374470b320b6b90fa5bc748770037974f434025fe3df79fc342
+size 2863