CL-From-Nothing/student_prefix_kukurasu_20K_continual_Qwen3_4B_Thinking_qwen3-1.7b_epoch_3_mask
TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kPublished:Mar 21, 2026Architecture:Transformer Warm
Loading preview...
Loading preview...