{
  "architectures": [
    "HYV3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 120000,
  "dtype": "bfloat16",
  "enable_attention_fp32_softmax": false,
  "enable_lm_head_fp32": true,
  "enable_moe_fp32_combine": false,
  "eod_token_id": 120026,
  "eos_token_id": 120025,
  "expert_hidden_dim": 1536,
  "first_k_dense_replace": 1,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.006,
  "intermediate_size": 13312,
  "max_position_embeddings": 262144,
  "mlp_bias": false,
  "mlp_layer_types": [
    "dense",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse",
    "sparse"
  ],
  "model_type": "hy_v3",
  "moe_intermediate_size": 1536,
  "moe_router_enable_expert_bias": true,
  "moe_router_use_sigmoid": true,
  "num_attention_heads": 64,
  "num_experts": 192,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 80,
  "num_key_value_heads": 8,
  "num_nextn_predict_layers": 1,
  "num_shared_experts": 1,
  "output_router_logits": true,
  "pad_token_id": 120002,
  "qk_norm": true,
  "quantization_config": {
    "bits": 4,
    "checkpoint_format": "gptq",
    "desc_act": false,
    "dynamic": {
      "+:.*experts": {
        "bits": 4,
        "group_size": 64
      },
      "+:.*shared_mlp": {
        "bits": 4,
        "group_size": 64
      }
    },
    "format": "gptq",
    "group_size": 128,
    "lm_head": false,
    "meta": {
      "act_group_aware": null,
      "auto_forward_data_parallel": true,
      "damp_auto_increment": null,
      "damp_percent": null,
      "dense_vram_strategy": "exclusive",
      "dense_vram_strategy_devices": null,
      "fallback": {
        "smooth": null,
        "strategy": "rtn",
        "threshold": "0.5%"
      },
      "foem": null,
      "gc_mode": "on_stage_end",
      "gptaq": null,
      "moe_vram_strategy": "exclusive",
      "moe_vram_strategy_devices": null,
      "mse": null,
      "offload_to_disk": true,
      "offload_to_disk_path": "/home/ubuntu/tmp_for_install/gptqmodel_kctb93p5",
      "pack_impl": "cpu",
      "quantizer": [
        "gptqmodel:7.2.0"
      ],
      "static_groups": null,
      "true_sequential": true,
      "uri": "https://github.com/modelcloud/gptqmodel",
      "wait_for_submodule_finalizers": true,
      "weight_only": {
        "smooth": null
      }
    },
    "method": "gptq",
    "pack_dtype": "int32",
    "quant_method": "gptq",
    "sym": true
  },
  "rms_norm_eps": 1e-05,
  "rope_parameters": {
    "rope_theta": 11158840.0,
    "rope_type": "default"
  },
  "route_norm": true,
  "router_scaling_factor": 2.826,
  "sep_token_id": 120007,
  "tie_word_embeddings": false,
  "transformers_version": "5.9.0",
  "use_cache": true,
  "use_grouped_mm": false,
  "vocab_size": 120832
}