prithivMLmods/Kepler-186f-Qwen3-Instruct-4B
Abliterated vs Qwen/Qwen3-4B-Instruct-2507. Looks like abliteration (refusal removal): only the output projections (down_proj, embed_tokens, o_proj) changed, in 36 of 36 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 1/1, Norms 0/145, MLP 36/108, Attention 36/144
3 derivatives checked
- mradermacher/Kepler-186f-Qwen3-Instruct-4B-i1-GGUF: Quantization
- prithivMLmods/Kepler-186f-Qwen3-Instruct-4B-GGUF: Same weights, converted
- mradermacher/Kepler-186f-Qwen3-Instruct-4B-GGUF: Same weights, converted