thaoshibe/relsim-qwenvl25-lora
Adapter vs Qwen/Qwen2.5-VL-7B-Instruct. thaoshibe/relsim-qwenvl25-lora is a LoRA adapter, not full weights: rank 16, on q_proj, v_proj in 28 layers (56 adapted matrices). It modifies Qwen/Qwen2.5-VL-7B-Instruct at load time.