DavidAU/OpenAI-gpt-oss-20B-INSTRUCT-Heretic-Uncensored-MXFP4
LoRA-style vs huihui-ai/Huihui-gpt-oss-20b-mxfp4-abliterated-v2. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/192, Attention 96/216, lm_head 0/1