Joyce94/LLM-RLHF-Tuning
LLM Tuning with PEFT (SFT+RM+PPO+DPO with LoRA)
This project helps machine learning engineers and researchers fine-tune large language models (LLMs) to better align with human preferences. You input a base LLM (like LLaMA or LLaMA2) and a dataset of desired responses, and it outputs a refined, instruction-tuned LLM capable of generating more helpful and harmless text. It's designed for those who want to enhance the performance and safety of their generative AI models.
453 stars. No commits in the last 6 months.
Use this if you need to significantly improve your LLM's ability to follow specific instructions and produce outputs that meet human quality standards, especially when working with LLaMA or LLaMA2 models.
Not ideal if you are looking for an out-of-the-box solution for non-LLM machine learning tasks or if you need to train models other than LLaMA or LLaMA2.
Stars
453
Forks
23
Language
Python
License
—
Category
Last pushed
Oct 11, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Joyce94/LLM-RLHF-Tuning"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
unslothai/unsloth
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama,...
huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5,...
oumi-ai/oumi
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!
linkedin/Liger-Kernel
Efficient Triton Kernels for LLM Training