tyzhu
/

mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8

Model card Files Files and versions

mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8 / global_step_50 /actor

14.4 GB

1 contributor

History: 1 commit

tyzhu's picture

mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8 to hf at time 2025-09-28 06:01:07

2d44a7d verified 11 days ago

huggingface
mathmedium2-mutualposclip0.0-llama3.2-3b-it-oldreward-4k-corrupt-0.8 to hf at time 2025-09-28 06:01:07 11 days ago