Models and data for the paper: Bradley-Terry Policy Optimization for Generative Preference Modeling
Shengyu Feng
shengyuf
·
AI & ML interests
None yet
Recent Activity
updated a collection 5 days ago
BTPO updated a model 5 days ago
shengyuf/Qwen2.5-3B-math-grm updated a collection 5 days ago
BTPOOrganizations
models 16
shengyuf/Qwen2.5-3B-math-grm
3B • Updated • 16
shengyuf/Qwen2.5-7B-math-grm
8B • Updated • 11
shengyuf/Llama3.2-3B-math-rm
3B • Updated • 16
shengyuf/Llama3.2-3B-if-rm
3B • Updated • 16
shengyuf/Llama3.2-3B-hh-rm
3B • Updated • 16
shengyuf/Llama3.1-8B-math-rm
8B • Updated • 17
shengyuf/Llama3.1-8B-if-rm
8B • Updated • 18
shengyuf/Llama3.1-8B-hh-rm
8B • Updated • 17
shengyuf/Qwen2.5-7B-math-rm
7B • Updated • 16
shengyuf/Qwen2.5-7B-if-rm
7B • Updated • 17