alimpfard/diffusiongemma-ft-grammar
LoRA-style vs unsloth/diffusiongemma-26B-A4B-it. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 30 of 30 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, MLP 90/234, Norms 0/434, other 0/152, Attention 115/223