liziniu/ReMax

Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)

29
/ 100
Experimental

This project offers a method for improving large language models (LLMs) to better align with human preferences. It takes an existing large language model and human feedback data, then uses reinforcement learning to produce a fine-tuned model that generates more desirable responses. AI researchers, machine learning engineers, and data scientists working on developing or deploying LLMs would use this.

201 stars. No commits in the last 6 months.

Use this if you need to fine-tune a large language model to be more helpful, harmless, or align with specific quality criteria, especially when GPU memory or training time is a constraint.

Not ideal if you are not working with large language models or do not have access to GPU resources for model training.

large-language-models reinforcement-learning model-alignment AI-model-training natural-language-processing
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

201

Forks

14

Language

Python

License

Last pushed

Dec 16, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/liziniu/ReMax"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.