Qwen3.8-27B Humanlike Chat 2.0 Released
A developer released Humanlike Chat 2.0, a Qwen3.8-27B LoRA fine-tune trained with on-policy distillation that fixes v1's lack of tool use, short replies and single personality, adding tool calls, instruction following and code/math ability. Version 1 drew 700+ upvotes, 248 comments and 44k downloads.