{
  "architectures": [
    "Qwen3_5ForConditionalGeneration"
  ],
  "image_token_id": 248056,
  "model_type": "qwen3_5",
  "quantization": {
    "group_size": 64,
    "bits": 4,
    "mode": "affine",
    "language_model.model.embed_tokens": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.mlp.gate_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.mlp.down_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.1.mlp.down_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.2.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.2.mlp.down_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.3.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.3.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.3.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.3.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.3.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.3.mlp.down_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.3.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.4.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.4.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.4.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.4.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.4.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.4.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.4.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.4.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.5.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.5.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.6.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.6.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.7.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.7.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.7.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.7.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.7.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.7.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.7.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.8.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.8.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.8.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.8.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.8.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.8.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.8.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.8.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.9.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.9.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.9.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.9.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.9.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.9.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.9.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.9.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.10.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.10.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.10.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.10.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.10.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.10.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.10.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.10.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.11.self_attn.q_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.11.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.11.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.11.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.11.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.11.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.11.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.12.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.12.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.12.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.12.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.12.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.12.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.12.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.12.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.13.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.13.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.13.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.13.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.13.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.13.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.13.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.13.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.14.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.14.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.14.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.14.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.14.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.14.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.14.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.14.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.15.self_attn.q_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.15.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.15.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.15.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.15.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.15.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.15.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.16.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.16.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.16.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.16.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.16.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.16.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.16.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.16.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.17.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.17.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.17.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.17.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.17.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.17.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.17.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.17.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.18.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.18.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.18.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.18.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.18.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.18.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.18.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.18.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.19.self_attn.q_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.19.self_attn.k_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.19.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.19.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.19.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.19.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.19.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.20.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.20.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.20.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.20.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.20.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.20.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.20.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.20.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.21.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.21.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.21.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.21.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.21.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.21.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.21.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.21.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.22.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.22.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.22.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.22.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.22.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.22.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.22.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.22.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.23.self_attn.q_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.23.self_attn.k_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.23.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.23.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.23.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.23.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.23.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.24.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.24.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.24.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.24.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.24.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.24.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.24.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.24.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.25.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.25.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.25.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.25.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.25.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.25.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.25.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.25.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.26.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.26.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.26.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.26.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.26.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.26.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.26.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.26.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.27.self_attn.q_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.27.self_attn.k_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.27.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.27.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.27.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.27.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.27.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.28.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.28.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.28.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.28.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.28.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.28.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.28.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.28.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.29.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.29.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.29.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.29.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.29.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.29.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.29.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.29.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.30.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.30.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.30.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.30.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.30.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.30.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.30.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.30.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.31.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.mlp.gate_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.mlp.down_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.lm_head": {
      "bits": 8,
      "group_size": 64
    }
  },
  "quantization_config": {
    "group_size": 64,
    "bits": 4,
    "mode": "affine",
    "language_model.model.embed_tokens": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.mlp.gate_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.mlp.down_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.1.mlp.down_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.2.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.2.mlp.down_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.3.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.3.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.3.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.3.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.3.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.3.mlp.down_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.3.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.4.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.4.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.4.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.4.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.4.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.4.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.4.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.4.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.5.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.5.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.6.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.6.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.7.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.7.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.7.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.7.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.7.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.7.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.7.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.8.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.8.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.8.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.8.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.8.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.8.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.8.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.8.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.9.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.9.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.9.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.9.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.9.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.9.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.9.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.9.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.10.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.10.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.10.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.10.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.10.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.10.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.10.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.10.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.11.self_attn.q_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.11.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.11.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.11.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.11.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.11.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.11.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.12.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.12.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.12.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.12.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.12.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.12.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.12.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.12.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.13.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.13.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.13.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.13.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.13.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.13.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.13.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.13.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.14.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.14.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.14.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.14.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.14.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.14.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.14.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.14.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.15.self_attn.q_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.15.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.15.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.15.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.15.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.15.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.15.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.16.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.16.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.16.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.16.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.16.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.16.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.16.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.16.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.17.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.17.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.17.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.17.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.17.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.17.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.17.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.17.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.18.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.18.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.18.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.18.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.18.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.18.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.18.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.18.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.19.self_attn.q_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.19.self_attn.k_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.19.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.19.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.19.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.19.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.19.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.20.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.20.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.20.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.20.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.20.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.20.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.20.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.20.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.21.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.21.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.21.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.21.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.21.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.21.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.21.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.21.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.22.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.22.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.22.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.22.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.22.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.22.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.22.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.22.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.23.self_attn.q_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.23.self_attn.k_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.23.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.23.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.23.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.23.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.23.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.24.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.24.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.24.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.24.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.24.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.24.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.24.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.24.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.25.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.25.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.25.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.25.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.25.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.25.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.25.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.25.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.26.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.26.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.26.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.26.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.26.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.26.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.26.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.26.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.27.self_attn.q_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.27.self_attn.k_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.27.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.27.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.27.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.27.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.27.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.28.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.28.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.28.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.28.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.28.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.28.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.28.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.28.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.29.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.29.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.29.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.29.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.29.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.29.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.29.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.29.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.30.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.30.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.30.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.30.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.30.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.30.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.30.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.30.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.31.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.mlp.gate_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.mlp.down_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.lm_head": {
      "bits": 8,
      "group_size": 64
    }
  },
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attn_output_gate": true,
    "dtype": "bfloat16",
    "eos_token_id": 248044,
    "full_attention_interval": 4,
    "head_dim": 256,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "initializer_range": 0.02,
    "intermediate_size": 12288,
    "layer_types": [
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention"
    ],
    "linear_conv_kernel_dim": 4,
    "linear_key_head_dim": 128,
    "linear_num_key_heads": 16,
    "linear_num_value_heads": 32,
    "linear_value_head_dim": 128,
    "max_position_embeddings": 262144,
    "mlp_only_layers": [],
    "model_type": "qwen3_5_text",
    "mtp_num_hidden_layers": 1,
    "mtp_use_dedicated_embeddings": false,
    "num_attention_heads": 16,
    "num_hidden_layers": 32,
    "num_key_value_heads": 4,
    "rms_norm_eps": 1e-06,
    "use_cache": true,
    "vocab_size": 248320,
    "mamba_ssm_dtype": "float32",
    "rope_parameters": {
      "mrope_interleaved": true,
      "mrope_section": [
        11,
        11,
        10
      ],
      "rope_theta": 10000000,
      "partial_rotary_factor": 0.25,
      "type": "default"
    }
  },
  "tie_word_embeddings": false,
  "transformers_version": "4.57.0.dev0",
  "video_token_id": 248057,
  "vision_end_token_id": 248054,
  "vision_start_token_id": 248053,
  "mtp_file": "mtp.safetensors",
  "mtp_tensor_count": 29,
  "mtp_policy": "optiq-int4-prequantized-gs64",
  "mtplx_mtp_quantization": {
    "bits": 4,
    "group_size": 64,
    "mode": "affine",
    "policy": "cyankiwi",
    "prequantized": true
  },
  "mtp_num_hidden_layers": 1,
  "vision_config": {
    "deepstack_visual_indexes": [],
    "depth": 27,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "in_channels": 3,
    "initializer_range": 0.02,
    "intermediate_size": 4304,
    "model_type": "qwen3_5",
    "num_heads": 16,
    "num_position_embeddings": 2304,
    "out_hidden_size": 4096,
    "patch_size": 16,
    "spatial_merge_size": 2,
    "temporal_patch_size": 2
  },
  "optiq_vision": {
    "sidecar": "optiq_vision.safetensors",
    "dtype": "bfloat16",
    "n_tensors": 333,
    "base_model": "mlx-community/Qwen3.5-9B-bf16"
  }
}