tyzhu
/

verl_checkpoints_sd_aug31

Model card Files Files and versions

verl_checkpoints_sd_aug31 / mathhard2-mutualpos0.2-qwen2.5-3b-old0.0reward-token_id-4k

68 GB

1 contributor

History: 1 commit

tyzhu's picture

verl_checkpoints_sd_aug31 to hf at time 2025-09-04 06:55:16

9edab9a verified 15 days ago

actor
verl_checkpoints_sd_aug31 to hf at time 2025-09-04 06:55:16 15 days ago