Repository Showcase
A curated collection of interesting GitHub repositories
BatsResearch/bonito
Converts unannotated text into instruction tuning datasets
Related repos
- tools for finetuning language models with instruction datasets and preference optimization
- LLaMA Factory is a framework for fine-tuning large language models
- parallel training for language models with dataset prep and programmatic access
- bash test framework for scripts and unix tools
- Toolkit for serving and running large language models through an inference server
- Text-to-dialogue model, clones voices
- multilingual OCR and document parsing toolkit
- Open-source toolkit for training and generating videos from text or other data inputs
- evaluating large language models across tasks and datasets
- open-weight text-to-speech model for fast, natural voice synthesis
