Joyce94/LLM-RLHF-Tuning
A complete RLHF training framework implementing SFT, reward modeling, PPO, and DPO for fine-tuning language models with LoRA/PEFT.
Not currently ranked — collecting fresh signals.
star history
This repository provides a from-scratch implementation of the three-stage RLHF (Reinforcement Learning from Human Feedback) training pipeline for large language models. It supports supervised fine-tuning (SFT), reward model (RM) training, PPO (Proximal Policy Optimization) training, and DPO (Direct Preference Optimization) training. The framework leverages PEFT and LoRA for parameter-efficient fine-tuning, supporting LLaMA, LLaMA2, and Alpaca models with distributed training via accelerate and DeepSpeed.
Frequently asked
- What is Joyce94/LLM-RLHF-Tuning?
- A complete RLHF training framework implementing SFT, reward modeling, PPO, and DPO for fine-tuning language models with LoRA/PEFT.
- Is LLM-RLHF-Tuning open source?
- Yes — Joyce94/LLM-RLHF-Tuning is an open-source project tracked on heatdrop.
- What language is LLM-RLHF-Tuning written in?
- Joyce94/LLM-RLHF-Tuning is primarily written in Python.
- How popular is LLM-RLHF-Tuning?
- Joyce94/LLM-RLHF-Tuning has 451 stars on GitHub.
- Where can I find LLM-RLHF-Tuning?
- Joyce94/LLM-RLHF-Tuning is on GitHub at https://github.com/Joyce94/LLM-RLHF-Tuning.