PreciseCoder
/

PreciseCoder-27B-GRPO-U

Reinforcement Learning

Model card Files Files and versions

PreciseCoder-27B-GRPO-U

Commit History

model card

ca1a0f5
verified

jameszhan33 commited on 4 days ago

qwen36-27b-GRPO_unit_h200 global_step_328 (merged FSDP->HF)

e24c81e
verified

jameszhan33 commited on 4 days ago

initial commit

a12ad48
verified

jameszhan33 commited on 4 days ago