aipib/Florence-2-VQAJP2
LoRA-style vs microsoft/Florence-2-base-ft. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of fc2, k_proj, q_proj, v_proj changed, in 6 of 6 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/9, Norms 0/166, other 0/107, Attention 54/240, MLP 12/144