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

InternLM/OREAL

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

Owner
InternLM (organization)
Stars
Stars: 189
Forks
Forks: 6
Language
Python
License
Apache-2.0
Created
2025
Topics
llmmathematicsreasoningrlo1
Tier
Prototype (100 to 249 ★) What this tier means
View on GitHub

More repos by InternLM

All 26 repos by InternLM

Nearby in Python

All Python repos