Johnny1024/bs16-k20-lr5e-7-ema0-eopd0.8-qwen3-4b-think-mmlu_pro_train10k_bottom20-s150

TEXT GENERATIONConcurrency Cost:1Model Size:4BQuant:BF16Ctx Length:32kPublished:Apr 28, 2026Architecture:Transformer Cold

Loading preview...