sulpikar2/Qwen3.6-27B-Ultimate-Uncensored-heretic
LoRA-style vs Qwen/Qwen3.6-27B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of conv1d, down_proj, o_proj, out_proj changed, in 49 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, MLP 49/304, Attention 39/556, lm_head 0/1, Norms 0/319