Lokeshgiri/CyberQwen2.5-Coder-7B
Adapter vs unsloth/Qwen2.5-Coder-7B-Instruct. Lokeshgiri/CyberQwen2.5-Coder-7B is a LoRA adapter, not full weights: rank 16, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 28 layers (196 adapted matrices). It modifies unsloth/Qwen2.5-Coder-7B-Instruct at load time.