minchaoh2002/PK-Link-Qwen3-8B-SFT-GRPO-self-judge-0.02-kl-4e-6_step_35
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Mar 26, 2026Architecture:Transformer Cold

Loading preview...

Finetunes
1 models