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

PrototypeCommon

yihedeng9/rlhf-summary-notes

A brief and partial summary of RLHF algorithms.

Owner: yihedeng9 (personal account)
Stars: Stars: 154
Forks: Forks: 3
Language: No language
License: None
Created: 2024
Topics: deep-learninglarge-language-modelspost-trainingreinforcement-learningrlhf
Tier: Prototype (100 to 249 ★) What this tier means