GitMylo/nsfwvision-qwen3-vl-8b-v3-gguf

Abliterated (fewer layers) vs Qwen/Qwen3-VL-8B-Instruct. GitMylo/nsfwvision-qwen3-vl-8b-v3-gguf matches part of Qwen/Qwen3-VL-8B-Instruct (399 of its 750 tensors; the rest of Qwen/Qwen3-VL-8B-Instruct has no counterpart). On the shared part: GitMylo/nsfwvision-qwen3-vl-8b-v3-gguf is a GGUF (F16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 36 of 36 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.

Tensors changed: Embeddings 0/1, Norms 0/145, MLP 36/108, Attention 36/144, lm_head 0/1

On the Hub · Downloads on Model Pulse