{
  "bits": 4,
  "data_type": "int",
  "group_size": 128,
  "sym": true,
  "iters": 400,
  "static_attention_granularity": "tensor",
  "static_kv_granularity": "tensor",
  "autoround_version": "0.15.0",
  "block_name_to_quantize": "model.language_model.layers",
  "quant_method": "auto-round",
  "packing_format": "auto_round:auto_gptq",
  "extra_config": {
    "model.language_model.layers.1.linear_attn.in_proj_a": {
      "bits": 8
    },
    "model.language_model.layers.1.linear_attn.in_proj_b": {
      "bits": 8
    },
    "model.language_model.layers.2.mlp.gate_proj": {
      "bits": 8
    },
    "model.language_model.layers.2.mlp.up_proj": {
      "bits": 8
    },
    "model.language_model.layers.2.linear_attn.in_proj_a": {
      "bits": 8
    },
    "model.language_model.layers.2.linear_attn.in_proj_b": {
      "bits": 8
    },
    "model.language_model.layers.3.mlp.gate_proj": {
      "bits": 8
    },
    "model.language_model.layers.3.mlp.up_proj": {
      "bits": 8
    },
    "model.language_model.layers.4.linear_attn.in_proj_a": {
      "bits": 8
    },
    "model.language_model.layers.4.linear_attn.in_proj_b": {
      "bits": 8
    },
    "model.language_model.layers.5.linear_attn.in_proj_a": {
      "bits": 8
    },
    "model.language_model.layers.5.linear_attn.in_proj_b": {
      "bits": 8
    },
    "model.language_model.layers.6.linear_attn.in_proj_a": {
      "bits": 8
    },
    "model.language_model.layers.6.linear_attn.in_proj_b": {
      "bits": 8
    },
    "model.language_model.layers.8.linear_attn.in_proj_a": {
      "bits": 8
    },
    "model.language_model.layers.8.linear_attn.in_proj_b": {
      "bits": 8
    },
    "model.language_model.layers.9.linear_attn.in_proj_a": {
      "bits": 8
    },
    "model.language_model.layers.9.linear_attn.in_proj_b": {
      "bits": 8
    },
    "model.language_model.layers.10.linear_attn.in_proj_a": {
      "bits": 8
    },
    "model.language_model.layers.10.linear_attn.in_proj_b": {
      "bits": 8
    },
    "model.language_model.layers.12.linear_attn.in_proj_a": {
      "bits": 8
    },
    "model.language_model.layers.12.linear_attn.in_proj_b": {
      "bits": 8
    },
    "model.language_model.layers.13.linear_attn.in_proj_a": {
      "bits": 8
    },
    "model.language_model.layers.13.linear_attn.in_proj_b": {
      "bits": 8
    },
    "model.language_model.layers.0.linear_attn.out_proj": {
      "bits": 8
    },
    "model.language_model.layers.1.linear_attn.out_proj": {
      "bits": 8
    },
    "model.language_model.layers.1.mlp.down_proj": {
      "bits": 8
    },
    "model.language_model.layers.2.linear_attn.out_proj": {
      "bits": 8
    },
    "model.language_model.layers.2.mlp.down_proj": {
      "bits": 8
    },
    "model.language_model.layers.3.self_attn.o_proj": {
      "bits": 8
    },
    "model.language_model.layers.3.mlp.down_proj": {
      "bits": 8
    },
    "model.language_model.layers.4.linear_attn.out_proj": {
      "bits": 8
    },
    "model.language_model.layers.4.mlp.down_proj": {
      "bits": 8
    },
    "model.language_model.layers.5.linear_attn.out_proj": {
      "bits": 8
    },
    "model.language_model.layers.6.linear_attn.out_proj": {
      "bits": 8
    },
    "model.language_model.layers.7.self_attn.o_proj": {
      "bits": 8
    },
    "model.language_model.layers.9.linear_attn.out_proj": {
      "bits": 8
    },
    "model.language_model.layers.11.self_attn.o_proj": {
      "bits": 8
    },
    "model.language_model.layers.15.self_attn.o_proj": {
      "bits": 8
    }
  }
}