lightonai/MonoQwen2-VL-v0.1
Adapter vs Qwen/Qwen2-VL-2B-Instruct. lightonai/MonoQwen2-VL-v0.1 is a LoRA adapter, not full weights: rank 32, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 28 layers (196 adapted matrices). It modifies Qwen/Qwen2-VL-2B-Instruct at load time.