AnalysisAI Models
Jun 23, 10:01 PM
Qwable 27B fine-tune mimics Claude Fable's reasoning
Qwable is a full fine-tune of Alibaba's Qwen3.6-27B on a dataset of Fable 5-style reasoning examples. An abliterated version removes built-in refusal behavior. Both run locally at no cost, requiring neither Anthropic's API nor its safeguards.
·
Jun 23, 10:01 PM