mradermacher/Qwen3-0.6B-gabliterated-GGUF
Abliterated vs Goekdeniz-Guelmez/Qwen3-0.6B-gabliterated. mradermacher/Qwen3-0.6B-gabliterated-GGUF is a GGUF (F16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 24 of 28 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/113, MLP 24/84, Attention 24/112