Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
PrototypeCommon

lucidrains/llama-qrlhf

Implementation of the Llama architecture with RLHF + Q-learning

Owner
lucidrains (personal account)
Stars
Stars: 170
Forks
Forks: 8
Language
Python
License
MIT
Created
2023
Topics
artificial-intelligenceattentiondeep-learningq-learning
Tier
Prototype (100 to 249 ★) What this tier means
View on GitHub

More repos by lucidrains

All 175 repos by lucidrains

Nearby in Python

All Python repos