Haon-Chen/e5-omni-3B
LoRA-style vs Qwen/Qwen2.5-Omni-3B. 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 20 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: other 0/7, MLP 57/381, Norms 0/233, Attention 76/613, Embeddings 0/1, lm_head 0/1