jimfhahn/bibframe-olmo3-v3
LoRA-style vs allenai/Olmo-3-7B-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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, MLP 96/96, Norms 0/129, Attention 128/128, lm_head 0/1