The Fine-Tuning Index / RLHF & Preference / #66
Sphere-AI-Lab/orbit
by Sphere-AI-Lab · RLHF & Preference · updated 1mo ago
Stable and Efficient Reinforcement Learning for Trillion-Parameter LLMs
48
momentum
157
stars
10
forks
#66
rank
cudalow-precisionpeftreinforcement-learningtransformers
View on GitHub →