Harsha901/llama3.2-11B-VL-Radiology-Captioning
LoRA-style vs unsloth/Llama-3.2-11B-Vision-Instruct. 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 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/10, Norms 0/261, MLP 120/288, Attention 160/344, lm_head 0/1, other 0/2