{
  "architectures": [
    "Qwen2MoeForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "decoder_sparse_step": 1,
  "eos_token_id": 151645,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5632,
  "max_position_embeddings": 32768,
  "max_window_layers": 21,
  "mlp_only_layers": [],
  "model_type": "qwen2_moe",
  "moe_intermediate_size": 1408,
  "norm_topk_prob": false,
  "num_attention_heads": 16,
  "num_experts": 60,
  "num_experts_per_tok": 4,
  "num_hidden_layers": 24,
  "num_key_value_heads": 16,
  "output_router_logits": false,
  "qkv_bias": true,
  "quantization_config": {
    "algo_config": null,
    "exclude": [
      "model.layers.0.mlp.gate",
      "model.layers.0.mlp.shared_expert_gate",
      "model.layers.1.mlp.gate",
      "model.layers.1.mlp.shared_expert_gate",
      "model.layers.2.mlp.gate",
      "model.layers.2.mlp.shared_expert_gate",
      "model.layers.3.mlp.gate",
      "model.layers.3.mlp.shared_expert_gate",
      "model.layers.4.mlp.gate",
      "model.layers.4.mlp.shared_expert_gate",
      "model.layers.5.mlp.gate",
      "model.layers.5.mlp.shared_expert_gate",
      "model.layers.6.mlp.gate",
      "model.layers.6.mlp.shared_expert_gate",
      "model.layers.7.mlp.gate",
      "model.layers.7.mlp.shared_expert_gate",
      "model.layers.8.mlp.gate",
      "model.layers.8.mlp.shared_expert_gate",
      "model.layers.9.mlp.gate",
      "model.layers.9.mlp.shared_expert_gate",
      "model.layers.10.mlp.gate",
      "model.layers.10.mlp.shared_expert_gate",
      "model.layers.11.mlp.gate",
      "model.layers.11.mlp.shared_expert_gate",
      "model.layers.12.mlp.gate",
      "model.layers.12.mlp.shared_expert_gate",
      "model.layers.13.mlp.gate",
      "model.layers.13.mlp.shared_expert_gate",
      "model.layers.14.mlp.gate",
      "model.layers.14.mlp.shared_expert_gate",
      "model.layers.15.mlp.gate",
      "model.layers.15.mlp.shared_expert_gate",
      "model.layers.16.mlp.gate",
      "model.layers.16.mlp.shared_expert_gate",
      "model.layers.17.mlp.gate",
      "model.layers.17.mlp.shared_expert_gate",
      "model.layers.18.mlp.gate",
      "model.layers.18.mlp.shared_expert_gate",
      "model.layers.19.mlp.gate",
      "model.layers.19.mlp.shared_expert_gate",
      "model.layers.20.mlp.gate",
      "model.layers.20.mlp.shared_expert_gate",
      "model.layers.21.mlp.gate",
      "model.layers.21.mlp.shared_expert_gate",
      "model.layers.22.mlp.gate",
      "model.layers.22.mlp.shared_expert_gate",
      "model.layers.23.mlp.gate",
      "model.layers.23.mlp.shared_expert_gate",
      "lm_head"
    ],
    "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": {
        "ch_axis": -1,
        "dtype": "fp4",
        "group_size": 32,
        "is_dynamic": true,
        "is_mx_scale_constraint": false,
        "is_scale_quant": false,
        "mx_element_dtype": null,
        "observer_cls": "PerBlockMXObserver",
        "qscheme": "per_group",
        "round_method": "half_even",
        "scale_calculation_mode": "even",
        "scale_format": "e8m0",
        "scale_type": "float",
        "symmetric": null
      },
      "output_tensors": null,
      "target_device": null,
      "weight": {
        "ch_axis": -1,
        "dtype": "fp4",
        "group_size": 32,
        "is_dynamic": false,
        "is_mx_scale_constraint": false,
        "is_scale_quant": false,
        "mx_element_dtype": null,
        "observer_cls": "PerBlockMXObserver",
        "qscheme": "per_group",
        "round_method": "half_even",
        "scale_calculation_mode": "even",
        "scale_format": "e8m0",
        "scale_type": "float",
        "symmetric": null
      }
    },
    "layer_quant_config": {},
    "layer_type_quant_config": {},
    "quant_method": "quark",
    "quant_mode": "eager_mode",
    "softmax_quant_spec": null
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "router_aux_loss_coef": 0.001,
  "shared_expert_intermediate_size": 5632,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.3",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}