RL-Forgetting-Experiments-3
/

code-q25_3b-nobuf

Reinforcement Learning

code-generation

catastrophic-forgetting

Model card Files Files and versions

code-q25_3b-nobuf / global_step_270 /eval

Commit History

Oct 5 20 days ago

14:01
Add MBPP+ training-set eval pass@k summaries (10 checkpoints)

smilani

Verified signature
5421df2