ApolloRaines/Qwen2.5-14B-Noncompliant
Abliterated vs Qwen/Qwen2.5-14B-Instruct. Looks like abliteration (refusal removal): only the output projections (o_proj) changed, in 48 of 48 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 0/144, Attention 48/336, lm_head 0/1
2 derivatives checked
- mradermacher/Qwen2.5-14B-Noncompliant-i1-GGUF: Quantization
- mradermacher/Qwen2.5-14B-Noncompliant-GGUF: Quantization