{ "peft_type": "LORA", "r": 256, "lora_alpha": 256, "lora_dropout": 0.0, "bias": "none", "rank_pattern": { "model\\.language_model\\.layers\\.40\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.40\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.41\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.41\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.42\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.42\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.44\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.44\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.45\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.45\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.46\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.46\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.48\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.48\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.49\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.49\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.50\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.50\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.52\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.52\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.53\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.53\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.54\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.54\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.56\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.56\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.57\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.57\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.58\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.58\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.60\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.60\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.61\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.61\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.62\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.62\\.linear_attn\\.in_proj_b": 48 }, "alpha_pattern": { "model\\.language_model\\.layers\\.40\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.40\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.41\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.41\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.42\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.42\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.44\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.44\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.45\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.45\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.46\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.46\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.48\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.48\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.49\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.49\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.50\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.50\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.52\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.52\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.53\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.53\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.54\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.54\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.56\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.56\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.57\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.57\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.58\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.58\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.60\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.60\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.61\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.61\\.linear_attn\\.in_proj_b": 48, "model\\.language_model\\.layers\\.62\\.linear_attn\\.in_proj_a": 48, "model\\.language_model\\.layers\\.62\\.linear_attn\\.in_proj_b": 48 }, "target_modules": [ "model.language_model.layers.40.linear_attn.in_proj_a", "model.language_model.layers.40.linear_attn.in_proj_b", "model.language_model.layers.40.linear_attn.in_proj_qkv", "model.language_model.layers.40.linear_attn.in_proj_z", "model.language_model.layers.40.linear_attn.out_proj", "model.language_model.layers.40.mlp.down_proj", "model.language_model.layers.40.mlp.gate_proj", "model.language_model.layers.40.mlp.up_proj", "model.language_model.layers.41.linear_attn.in_proj_a", "model.language_model.layers.41.linear_attn.in_proj_b", "model.language_model.layers.41.linear_attn.in_proj_qkv", "model.language_model.layers.41.linear_attn.in_proj_z", "model.language_model.layers.41.linear_attn.out_proj", "model.language_model.layers.41.mlp.down_proj", "model.language_model.layers.41.mlp.gate_proj", "model.language_model.layers.41.mlp.up_proj", "model.language_model.layers.42.linear_attn.in_proj_a", "model.language_model.layers.42.linear_attn.in_proj_b", "model.language_model.layers.42.linear_attn.in_proj_qkv", "model.language_model.layers.42.linear_attn.in_proj_z", "model.language_model.layers.42.linear_attn.out_proj", "model.language_model.layers.42.mlp.down_proj", "model.language_model.layers.42.mlp.gate_proj", "model.language_model.layers.42.mlp.up_proj", "model.language_model.layers.43.mlp.down_proj", "model.language_model.layers.43.mlp.gate_proj", "model.language_model.layers.43.mlp.up_proj", "model.language_model.layers.43.self_attn.k_proj", "model.language_model.layers.43.self_attn.o_proj", "model.language_model.layers.43.self_attn.q_proj", "model.language_model.layers.43.self_attn.v_proj", "model.language_model.layers.44.linear_attn.in_proj_a", "model.language_model.layers.44.linear_attn.in_proj_b", "model.language_model.layers.44.linear_attn.in_proj_qkv", "model.language_model.layers.44.linear_attn.in_proj_z", "model.language_model.layers.44.linear_attn.out_proj", "model.language_model.layers.44.mlp.down_proj", "model.language_model.layers.44.mlp.gate_proj", "model.language_model.layers.44.mlp.up_proj", "model.language_model.layers.45.linear_attn.in_proj_a", "model.language_model.layers.45.linear_attn.in_proj_b", "model.language_model.layers.45.linear_attn.in_proj_qkv", "model.language_model.layers.45.linear_attn.in_proj_z", "model.language_model.layers.45.linear_attn.out_proj", "model.language_model.layers.45.mlp.down_proj", "model.language_model.layers.45.mlp.gate_proj", "model.language_model.layers.45.mlp.up_proj", "model.language_model.layers.46.linear_attn.in_proj_a", "model.language_model.layers.46.linear_attn.in_proj_b", "model.language_model.layers.46.linear_attn.in_proj_qkv", "model.language_model.layers.46.linear_attn.in_proj_z", "model.language_model.layers.46.linear_attn.out_proj", "model.language_model.layers.46.mlp.down_proj", "model.language_model.layers.46.mlp.gate_proj", "model.language_model.layers.46.mlp.up_proj", "model.language_model.layers.47.mlp.down_proj", "model.language_model.layers.47.mlp.gate_proj", "model.language_model.layers.47.mlp.up_proj", "model.language_model.layers.47.self_attn.k_proj", "model.language_model.layers.47.self_attn.o_proj", "model.language_model.layers.47.self_attn.q_proj", "model.language_model.layers.47.self_attn.v_proj", "model.language_model.layers.48.linear_attn.in_proj_a", "model.language_model.layers.48.linear_attn.in_proj_b", "model.language_model.layers.48.linear_attn.in_proj_qkv", "model.language_model.layers.48.linear_attn.in_proj_z", "model.language_model.layers.48.linear_attn.out_proj", "model.language_model.layers.48.mlp.down_proj", "model.language_model.layers.48.mlp.gate_proj", "model.language_model.layers.48.mlp.up_proj", "model.language_model.layers.49.linear_attn.in_proj_a", "model.language_model.layers.49.linear_attn.in_proj_b", "model.language_model.layers.49.linear_attn.in_proj_qkv", "model.language_model.layers.49.linear_attn.in_proj_z", "model.language_model.layers.49.linear_attn.out_proj", "model.language_model.layers.49.mlp.down_proj", "model.language_model.layers.49.mlp.gate_proj", "model.language_model.layers.49.mlp.up_proj", "model.language_model.layers.50.linear_attn.in_proj_a", "model.language_model.layers.50.linear_attn.in_proj_b", "model.language_model.layers.50.linear_attn.in_proj_qkv", "model.language_model.layers.50.linear_attn.in_proj_z", "model.language_model.layers.50.linear_attn.out_proj", "model.language_model.layers.50.mlp.down_proj", "model.language_model.layers.50.mlp.gate_proj", "model.language_model.layers.50.mlp.up_proj", "model.language_model.layers.51.mlp.down_proj", "model.language_model.layers.51.mlp.gate_proj", "model.language_model.layers.51.mlp.up_proj", "model.language_model.layers.51.self_attn.k_proj", "model.language_model.layers.51.self_attn.o_proj", "model.language_model.layers.51.self_attn.q_proj", "model.language_model.layers.51.self_attn.v_proj", "model.language_model.layers.52.linear_attn.in_proj_a", "model.language_model.layers.52.linear_attn.in_proj_b", "model.language_model.layers.52.linear_attn.in_proj_qkv", "model.language_model.layers.52.linear_attn.in_proj_z", "model.language_model.layers.52.linear_attn.out_proj", "model.language_model.layers.52.mlp.down_proj", "model.language_model.layers.52.mlp.gate_proj", "model.language_model.layers.52.mlp.up_proj", "model.language_model.layers.53.linear_attn.in_proj_a", "model.language_model.layers.53.linear_attn.in_proj_b", "model.language_model.layers.53.linear_attn.in_proj_qkv", "model.language_model.layers.53.linear_attn.in_proj_z", "model.language_model.layers.53.linear_attn.out_proj", "model.language_model.layers.53.mlp.down_proj", "model.language_model.layers.53.mlp.gate_proj", "model.language_model.layers.53.mlp.up_proj", "model.language_model.layers.54.linear_attn.in_proj_a", "model.language_model.layers.54.linear_attn.in_proj_b", "model.language_model.layers.54.linear_attn.in_proj_qkv", "model.language_model.layers.54.linear_attn.in_proj_z", "model.language_model.layers.54.linear_attn.out_proj", "model.language_model.layers.54.mlp.down_proj", "model.language_model.layers.54.mlp.gate_proj", "model.language_model.layers.54.mlp.up_proj", "model.language_model.layers.55.mlp.down_proj", "model.language_model.layers.55.mlp.gate_proj", "model.language_model.layers.55.mlp.up_proj", "model.language_model.layers.55.self_attn.k_proj", "model.language_model.layers.55.self_attn.o_proj", "model.language_model.layers.55.self_attn.q_proj", "model.language_model.layers.55.self_attn.v_proj", "model.language_model.layers.56.linear_attn.in_proj_a", "model.language_model.layers.56.linear_attn.in_proj_b", "model.language_model.layers.56.linear_attn.in_proj_qkv", "model.language_model.layers.56.linear_attn.in_proj_z", "model.language_model.layers.56.linear_attn.out_proj", "model.language_model.layers.56.mlp.down_proj", "model.language_model.layers.56.mlp.gate_proj", "model.language_model.layers.56.mlp.up_proj", "model.language_model.layers.57.linear_attn.in_proj_a", "model.language_model.layers.57.linear_attn.in_proj_b", "model.language_model.layers.57.linear_attn.in_proj_qkv", "model.language_model.layers.57.linear_attn.in_proj_z", "model.language_model.layers.57.linear_attn.out_proj", "model.language_model.layers.57.mlp.down_proj", "model.language_model.layers.57.mlp.gate_proj", "model.language_model.layers.57.mlp.up_proj", "model.language_model.layers.58.linear_attn.in_proj_a", "model.language_model.layers.58.linear_attn.in_proj_b", "model.language_model.layers.58.linear_attn.in_proj_qkv", "model.language_model.layers.58.linear_attn.in_proj_z", "model.language_model.layers.58.linear_attn.out_proj", "model.language_model.layers.58.mlp.down_proj", "model.language_model.layers.58.mlp.gate_proj", "model.language_model.layers.58.mlp.up_proj", "model.language_model.layers.59.mlp.down_proj", "model.language_model.layers.59.mlp.gate_proj", "model.language_model.layers.59.mlp.up_proj", "model.language_model.layers.59.self_attn.k_proj", "model.language_model.layers.59.self_attn.o_proj", "model.language_model.layers.59.self_attn.q_proj", "model.language_model.layers.59.self_attn.v_proj", "model.language_model.layers.60.linear_attn.in_proj_a", "model.language_model.layers.60.linear_attn.in_proj_b", "model.language_model.layers.60.linear_attn.in_proj_qkv", "model.language_model.layers.60.linear_attn.in_proj_z", "model.language_model.layers.60.linear_attn.out_proj", "model.language_model.layers.60.mlp.down_proj", "model.language_model.layers.60.mlp.gate_proj", "model.language_model.layers.60.mlp.up_proj", "model.language_model.layers.61.linear_attn.in_proj_a", "model.language_model.layers.61.linear_attn.in_proj_b", "model.language_model.layers.61.linear_attn.in_proj_qkv", "model.language_model.layers.61.linear_attn.in_proj_z", "model.language_model.layers.61.linear_attn.out_proj", "model.language_model.layers.61.mlp.down_proj", "model.language_model.layers.61.mlp.gate_proj", "model.language_model.layers.61.mlp.up_proj", "model.language_model.layers.62.linear_attn.in_proj_a", "model.language_model.layers.62.linear_attn.in_proj_b", "model.language_model.layers.62.linear_attn.in_proj_qkv", "model.language_model.layers.62.linear_attn.in_proj_z", "model.language_model.layers.62.linear_attn.out_proj", "model.language_model.layers.62.mlp.down_proj", "model.language_model.layers.62.mlp.gate_proj", "model.language_model.layers.62.mlp.up_proj", "model.language_model.layers.63.mlp.down_proj", "model.language_model.layers.63.mlp.gate_proj", "model.language_model.layers.63.mlp.up_proj", "model.language_model.layers.63.self_attn.k_proj", "model.language_model.layers.63.self_attn.o_proj", "model.language_model.layers.63.self_attn.q_proj", "model.language_model.layers.63.self_attn.v_proj" ], "base_model_name_or_path": "Qwen/Qwen3.8-27B", "task_type": null, "fan_in_fan_out": false, "init_lora_weights": true }