leeminwaan/qwen3.5_4B_AiO_LR_lora_kimi_k2.5_distilation
Adapter vs unsloth/Qwen3.5-4B. leeminwaan/qwen3.5_4B_AiO_LR_lora_kimi_k2.5_distilation is a LoRA adapter, not full weights: rank 64, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 32 layers (128 adapted matrices). It modifies unsloth/Qwen3.5-4B at load time.