henrywoo/chatllama
Open-source RLHF-based implementation for building ChatGPT-style assistants from LLaMA models.
Not currently ranked — collecting fresh signals.
star history
This repository provides a complete open-source implementation for fine-tuning LLaMA models using Reinforcement Learning from Human Feedback (RLHF) to create ChatGPT-style assistants. It supports all LLaMA model sizes (7B to 65B parameters) with built-in DeepSpeed ZERO acceleration for faster training. The library enables single-GPU inference and claims 15x faster training compared to the original ChatGPT while maintaining cost-effectiveness.
Frequently asked
- What is henrywoo/chatllama?
- Open-source RLHF-based implementation for building ChatGPT-style assistants from LLaMA models.
- Is chatllama open source?
- Yes — henrywoo/chatllama is an open-source project tracked on heatdrop.
- What language is chatllama written in?
- henrywoo/chatllama is primarily written in Python.
- How popular is chatllama?
- henrywoo/chatllama has 1.2k stars on GitHub.
- Where can I find chatllama?
- henrywoo/chatllama is on GitHub at https://github.com/henrywoo/chatllama.