Jiunsong/SuperQwen3.8-Flash-Next-abliterated-FP8-DGX-Spark
Abliterated vs Qwen/Qwen3.8-Flash-Next-FP8. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 12 of 48 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Norms 0/302, other 0/8, Attention 12/608, MLP 133/1943, Embeddings 0/138, lm_head 0/1