Egor Kreed

🚀 HuggingArtists Model - EGOR KREED

This model is designed to generate lyrics in the style of EGOR KREED. It was created using the huggingartists framework, allowing users to create their own artist - based bots.

🚀 Quick Start

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

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

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

Or with Transformers library:

from transformers import AutoTokenizer, AutoModelWithLMHead
  
tokenizer = AutoTokenizer.from_pretrained("huggingartists/egor-kreed")

model = AutoModelWithLMHead.from_pretrained("huggingartists/egor-kreed")

✨ Features

• Artist - specific generation: Generate lyrics in the style of EGOR KREED.
• Easy - to - use: Can be used with standard NLP libraries like transformers.

📦 Installation

No specific installation steps are provided in the original README. 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

💻 Usage Examples

Basic Usage

from transformers import pipeline
generator = pipeline('text-generation', model='huggingartists/egor-kreed')
print(generator("I am", num_return_sequences=1))

Advanced Usage

You can adjust the parameters of the pipeline or the AutoModelWithLMHead for more customized text generation. For example, you can change the max_length parameter to control the length of the generated text:

from transformers import pipeline
generator = pipeline('text-generation', model='huggingartists/egor-kreed')
print(generator("I am", num_return_sequences=1, max_length = 100))

📚 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 EGOR KREED. Dataset is available here. And can be used with:

from datasets import load_dataset

dataset = load_dataset("huggingartists/egor-kreed")

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 EGOR KREED'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 a pre - trained GPT - 2 model. The fine - tuning process is tracked using Weights & Biases (W&B) to ensure transparency and reproducibility. The training data consists of EGOR KREED's lyrics, which are used to adapt the model to the artist's style.

📄 License

No license information is provided in the original README.

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.