byroneverson/Yi-1.5-9B-Chat-16K-abliterated
Abliterated vs 01-ai/Yi-1.5-9B-Chat-16K. Looks like abliteration (refusal removal): only the output projections (down_proj, embed_tokens, 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 1/1, Norms 0/97, MLP 48/144, Attention 48/192, lm_head 0/1
2 derivatives checked
- mradermacher/Yi-1.5-9B-Chat-16K-abliterated-i1-GGUF: Quantization
- mradermacher/Yi-1.5-9B-Chat-16K-abliterated-GGUF: Same weights, converted