{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 128000,
  "dtype": "bfloat16",
  "eos_token_id": 128001,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "max_position_embeddings": 131072,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 16,
  "num_key_value_heads": 8,
  "pretraining_tp": 1,
  "quantization_config": {
    "algo_config": [
      {
        "model_decoder_layers": "model.layers",
        "name": "awq",
        "scaling_layers": [
          {
            "inp": "self_attn.q_proj",
            "layers": [
              "self_attn.q_proj",
              "self_attn.k_proj",
              "self_attn.v_proj"
            ],
            "module2inspect": "self_attn",
            "prev_op": "input_layernorm"
          },
          {
            "inp": "self_attn.o_proj",
            "layers": [
              "self_attn.o_proj"
            ],
            "prev_op": "self_attn.v_proj"
          },
          {
            "inp": "mlp.gate_proj",
            "layers": [
              "mlp.gate_proj",
              "mlp.up_proj"
            ],
            "module2inspect": "mlp",
            "prev_op": "post_attention_layernorm"
          },
          {
            "inp": "mlp.down_proj",
            "layers": [
              "mlp.down_proj"
            ],
            "prev_op": "mlp.up_proj"
          }
        ]
      }
    ],
    "exclude": [],
    "export": {
      "kv_cache_group": [],
      "min_kv_scale": 0.0,
      "pack_method": "reorder",
      "weight_format": "real_quantized",
      "weight_merge_groups": null
    },
    "global_quant_config": {
      "bias": null,
      "input_tensors": null,
      "output_tensors": null,
      "target_device": null,
      "weight": {
        "block_size": null,
        "ch_axis": -1,
        "dtype": "uint4",
        "enable_buffer_reuse": false,
        "group_size": 128,
        "is_dynamic": false,
        "is_scale_quant": false,
        "max_input_numel": 4194304,
        "mx_element_dtype": null,
        "observer_cls": "PerGroupMinMaxObserver",
        "qscheme": "per_group",
        "round_method": "half_even",
        "scale_calculation_mode": null,
        "scale_format": null,
        "scale_type": "float",
        "symmetric": false
      }
    },
    "kv_cache_post_rope": false,
    "kv_cache_quant_config": {},
    "layer_quant_config": {},
    "layer_type_quant_config": {},
    "quant_method": "quark",
    "quant_mode": "eager_mode",
    "softmax_quant_spec": null,
    "version": "0.12rc4"
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "factor": 32.0,
    "high_freq_factor": 4.0,
    "low_freq_factor": 1.0,
    "original_max_position_embeddings": 8192,
    "rope_type": "llama3"
  },
  "rope_theta": 500000.0,
  "tie_word_embeddings": true,
  "transformers_version": "4.57.6",
  "use_cache": true,
  "vocab_size": 128256
}