AliBilge/Huihui-GLM-4.6V-Flash-abliterated
Abliterated vs zai-org/GLM-4.6V-Flash. AliBilge/Huihui-GLM-4.6V-Flash-abliterated is a GGUF (FP16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 40 of 40 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 39/80, Attention 119/280, lm_head 0/1