bekoozkan/godot-qwen2.5-coder-3b-instruct
Adapter vs Qwen/Qwen2.5-Coder-3B-Instruct. bekoozkan/godot-qwen2.5-coder-3b-instruct is a LoRA adapter, not full weights: rank 8, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 36 layers (252 adapted matrices). It modifies Qwen/Qwen2.5-Coder-3B-Instruct at load time.