shengyuf/BTPO_data
Preview • Updated • 545
BTPO
Models and data for the paper: Bradley-Terry Policy Optimization for Generative Preference Modeling
-
-
shengyuf/Qwen2.5-3B-if-rm
3B • Updated • 4 -
shengyuf/Qwen2.5-7B-hh-rm
7B • Updated • 3 -
shengyuf/Qwen2.5-3B-math-rm
3B • Updated • 7 -
shengyuf/Qwen2.5-7B-math-rm
7B • Updated • 4 -
shengyuf/Qwen2.5-7B-if-rm
7B • Updated • 3 -
shengyuf/Qwen2.5-3B-hh-rm
3B • Updated • 3 -
shengyuf/Llama3.1-8B-hh-rm
8B • Updated • 2 -
shengyuf/Llama3.1-8B-if-rm
8B • Updated • 2 -
shengyuf/Llama3.1-8B-math-rm
8B • Updated • 2 -
shengyuf/Llama3.2-3B-if-rm
3B • Updated • 1 -
shengyuf/Llama3.2-3B-hh-rm
3B • Updated • 6 -
shengyuf/Llama3.2-3B-math-rm
3B • Updated • 1 -
shengyuf/Qwen2.5-7B-math-grm
8B • Updated • 2 -
shengyuf/Qwen2.5-3B-math-grm
3B • Updated • 2