hotdogs/Qwen3.8-27B-abliterated
Abliterated vs Qwen/Qwen3.8-27B. Looks like abliteration (refusal removal): only the output projections (down_proj, embed_tokens, o_proj, out_proj) changed, in 64 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Norms 0/325, Attention 65/560, MLP 65/307, Embeddings 1/5, lm_head 0/1, other 0/1
7 derivatives checked
- hotdogs/Qwen3.8-27B-abliterated-MTP-GGUF: Quantization
- hotdogs/Qwen3.8-27B-abliterated-AWQ-INT4: Quantization
- hotdogs/Qwen3.8-27B-thinkingcap-abliterated: LoRA-style
- hotdogs/Qwen3.8-27B-abliterated-cyber-preview: Different architecture
- Beached89/Qwen3.8-27B-Q3_K_XL-abliterated: Quantization
- hotdogs/Qwen3.8-27B-abliterated-code-analysis-preview: LoRA-style
- hotdogs/Qwen3.8-27B-abliterated-sme-preview: LoRA-style