max-rl
/

grpo_acecode87k_checkpoints

Model card Files Files and versions

grpo_acecode87k_checkpoints / global_step_300 /actor /huggingface

Commit History

Oct 28 9 days ago

17:06
global_step_300: bf16 HF export (no optimizer / FSDP state)

guanning

Verified signature
b72826e