AI가 움직이고 미래가 업데이트됩니다.Qwen3-8B-heretic
A decensored variant of Qwen/Qwen3-8B, produced with Heretic v1.4.0 (directional ablation / "abliteration"). Refusal behavior is suppressed via targeted weight edits to the attention output and MLP down-projections rather than fine-tuning, so the base model's knowledge and instruction-following are left largely intact. **Who this is for:** developers who want Qwen3's thinking/non-thinking dual-mode architecture without the refusal guardrails. Great for local agents, roleplay, and studying refusal mechanisms in reasoning-capable models. Supports both ` ` and direct-answer modes. Weights only, at this model's 8.2B native size; add ~1 GB for context. OOM? Drop one quant level. Headroom to spare? Go one up.
번역 준비 중입니다. 원문을 표시합니다.
A decensored variant of Qwen/Qwen3-8B, produced with Heretic v1.4.0 (directional ablation / "abliteration"). Refusal behavior is suppressed via targeted weight edits to the attention output and MLP down-projections rather than fine-tuning, so the base model's knowledge and instruction-following are left largely intact. **Who this is for:** developers who want Qwen3's thinking/non-thinking dual-mode architecture without the refusal guardrails. Great for local agents, roleplay, and studying refusal mechanisms in reasoning-capable models. Supports both ` ` and direct-answer modes. Weights only, at this model's 8.2B native size; add ~1 GB for context. OOM? Drop one quant level. Headroom to spare? Go one up.