Morgenshtern

🚀 HuggingArtists Model: MORGENSHTERN

This is a HuggingArtists model based on MORGENSHTERN. It can generate lyrics similar to MORGENSHTERN's style. You can create your own bot based on your favorite artist using this framework.

I was made with huggingartists.

Create your own bot based on your favorite artist with the demo!

🚀 Quick Start

You can use this model directly with a pipeline for text generation:

from transformers import pipeline
generator = pipeline('text-generation',
                     model='huggingartists/morgenshtern')
generator("I am", num_return_sequences=5)

Or with Transformers library:

from transformers import AutoTokenizer, AutoModelWithLMHead
  
tokenizer = AutoTokenizer.from_pretrained("huggingartists/morgenshtern")

model = AutoModelWithLMHead.from_pretrained("huggingartists/morgenshtern")

✨ Features

• Artist-Specific Lyrics Generation: Generate lyrics in the style of MORGENSHTERN.
• Easy to Use: Can be used with the Transformers library and Hugging Face datasets.

📦 Installation

There is no specific installation command provided in the original document. However, to use the model, you need to have the transformers and datasets libraries installed. You can install them using pip:

pip install transformers datasets

📚 Documentation

How does it work?

To understand how the model was developed, check the W&B report.

Training data

The model was trained on lyrics from MORGENSHTERN.

Dataset is available here. And can be used with:

from datasets import load_dataset

dataset = load_dataset("huggingartists/morgenshtern")

Explore the data, which is tracked with W&B artifacts at every step of the pipeline.

Training procedure

The model is based on a pre-trained GPT-2 which is fine-tuned on MORGENSHTERN's lyrics.

Hyperparameters and metrics are recorded in the W&B training run for full transparency and reproducibility.

At the end of training, the final model is logged and versioned.

🔧 Technical Details

The model is fine-tuned from GPT - 2 on MORGENSHTERN's lyrics. The training process is tracked by Weights & Biases (W&B) to ensure transparency and reproducibility.

📄 License

No license information is provided in the original document.

Limitations and bias

The model suffers from the same limitations and bias as GPT-2.

In addition, the data present in the user's tweets further affects the text generated by the model.

About

Built by Aleksey Korshuk

For more details, visit the project repository.