config.json

{
  "architectures": [
    "LlamaForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 11008,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "llama",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "pretraining_tp": 1,
  "quantization_config": {
    "algo_config": {
      "model_decoder_layers": "model.layers",
      "name": "awq",
      "num_attention_heads": -1,
      "num_key_value_heads": -1,
      "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": {
        "ch_axis": 1,
        "dtype": "uint4",
        "group_size": 128,
        "is_dynamic": false,
        "observer_cls": "PerGroupMinMaxObserver",
        "qscheme": "per_group",
        "round_method": "half_even",
        "scale_type": "float",
        "symmetric": false
      }
    },
    "layer_quant_config": {},
    "layer_type_quant_config": {},
    "quant_method": "quark",
    "quant_mode": "eager_mode",
    "softmax_quant_spec": null
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 10000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.50.3",
  "use_cache": true,
  "vocab_size": 32000
}