R-PRM: Reasoning-Driven Process Reward Modeling
Shuaijie She
kevinpro
AI & ML interests
Reasoning, Chain of Thoughts, Alignment, Factual Consistency, Summarization
Recent Activity
new activity
about 17 hours ago
ByteDance-Seed/Seed-X-PPO-7B:Output truncated without reason
new activity
1 day ago
ByteDance-Seed/Seed-X-PPO-7B:当上下文过长的时候，例如1w字，大模型一直输出一句话，另外思维链也无法通过提示词来关闭
Organizations
MAPO: Advancing Multilingual Reasoning through Multilingual Alignment‑as‑Preference
Optimization
-
3
Open Multilingual Reasoning Leaderboard
🦊Display and search a leaderboard of math models
-
MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization
Paper • 2401.06838 • Published -
kevinpro/MNumGLUESub
Updated • 6 -
kevinpro/MetaMathOctopus-MAPO-DPO-13B
Text Generation • 13B • Updated • 3
R-PRM: Reasoning-Driven Process Reward Modeling
MAPO: Advancing Multilingual Reasoning through Multilingual Alignment‑as‑Preference
Optimization
-
3
Open Multilingual Reasoning Leaderboard
🦊Display and search a leaderboard of math models
-
MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization
Paper • 2401.06838 • Published -
kevinpro/MNumGLUESub
Updated • 6 -
kevinpro/MetaMathOctopus-MAPO-DPO-13B
Text Generation • 13B • Updated • 3
models
16
kevinpro/Seed-X-PPO-7B-Q8_0-GGUF
8B
•
Updated
•
16
kevinpro/R-PRM-7B-DPO
Text Generation
•
8B
•
Updated
•
8
kevinpro/Hydra-LLaMA3-8B-0531-preview-Q4_K_M-GGUF
Text Generation
•
8B
•
Updated
•
1
kevinpro/MistralMathOctopus-7B
Text Generation
•
7B
•
Updated
•
2
kevinpro/MetaMathOctopus-MAPO-DPO-13B
Text Generation
•
13B
•
Updated
•
3
kevinpro/MathOctopus-MAPO-DPO-7B
Text Generation
•
7B
•
Updated
•
3
kevinpro/MetaMathOctopus-13B
Text Generation
•
13B
•
Updated
•
3
kevinpro/MetaMathOctopus-MAPO-DPO-7B
Text Generation
•
7B
•
Updated
•
4
kevinpro/MetaMathOctopus-7B
Text Generation
•
7B
•
Updated
•
3
kevinpro/MathOctopus-MAPO-DPO-13B
Text Generation
•
13B
•
Updated
•
6