CorrectKLinRL/Qwen3-1.7B-Base-dapo_filter-grpo-useKL_True-KLlossCoef1e-3
TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:May 4, 2026Architecture:Transformer Cold
Loading preview...
Loading preview...