Qwen2.5-1.5B on a support queue with tools: 11.79% base -> 87.19% SFT -> 96.07% GRPO on the dev exam.
-
monte-inc/qwen2.5-1.5b-cloudsync-support
Text Generation • Updated -
monte-inc/cloudsync-support-sft
Viewer • Updated • 1.93k • 55 -
monte-inc/qwen2.5-1.5b-cloudsync-support-resume-01M2HP4M1G955GXWV3XBFR5YT6-train110
Updated • 14 -
monte-inc/qwen2.5-1.5b-cloudsync-support-resume-01M2HK1C6W92J2VEWDFNX6GEXK-train60
Updated • 10