Zynerji/Ektome-Qwen2.5-1.5Bi-PristinelyUncensored
Abliterated vs Qwen/Qwen2.5-1.5B-Instruct. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 28 of 28 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 28/84, Attention 28/196
2 derivatives checked
- mradermacher/Ektome-Qwen2.5-1.5Bi-PristinelyUncensored-i1-GGUF: Quantization
- mradermacher/Ektome-Qwen2.5-1.5Bi-PristinelyUncensored-GGUF: Same weights, converted