tyzhu
/

mathhard2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8

Model card Files Files and versions

mathhard2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8

54.6 GB

1 contributor

History: 3 commits

tyzhu's picture

mathhard2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8 to hfat time 2025-09-27 16:39:16

43b636b verified 11 days ago

global_step_50
mathhard2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8 to hf at time 2025-09-27 16:30:03 11 days ago
.gitattributes

1.6 kB

mathhard2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8 to hf at time 2025-09-27 16:30:03 11 days ago
latest_checkpointed_iteration.txt

2 Bytes

mathhard2-mutualposclip0.5-llama3.2-3b-it-oldreward-4k-corrupt-0.8 to hfat time 2025-09-27 16:39:16 11 days ago