Name2Bio Model
This repository hosts the raw Hugging Face model files for the Name2Bio transformer model. This model is designed to generate creative character bios given an input name. It is based on the DistilGPT2 architecture and has been fine-tuned on a curated dataset of character names and bios.
There are traditional huggingface files, as well as name2bio.gguf, which is a llama.cpp model for faster CPU inference.
Overview
The Name2Bio model accepts a character name as input and generates a corresponding bio. The repository includes all the necessary files to load the model using the Hugging Face Transformers library.
How to Use
Installation
Install the required library:
pip install transformers
Loading the Model
You can load the model and generate a bio using the code from example_huggingface.py, and example_llama.py for Huggingface and Llama (faster CPU inference) respectively.
### Example Prompt
For example, the prompt:
[NAME] Goku [BIO]
will generate a creative biography for Goku.
## Intended Use Cases
- **Character Creation:** A tool for writers and creators to generate inspirational character bios.
- **Creative Storytelling:** Quickly generate detailed bios for fictional narratives.
- **Rapid Prototyping:** Iterate on character concepts with AI-generated suggestions.
## Model Training and Fine-Tuning
This model was fine-tuned on a dataset of character names and bios. For more details on the training process, please refer to [this repository](https://github.com/Pythonimous/ficbot-backend).
## Contact
For any questions or further information, please contact kir.nikolaev.7@gmail.com
---
Feel free to use and adapt this model for your projects!
- Downloads last month
- 9