{
  "architectures": [
    "HYV3ForCausalLM"
  ],
  "bos_token_id": 120000,
  "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,
  "moe_intermediate_size": 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,
  "model_type": "hy_v3",
  "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_shared_experts": 1,
  "output_router_logits": true,
  "pad_token_id": 120002,
  "qk_norm": 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": "5.6.0",
  "use_cache": true,
  "use_grouped_mm": false,
  "vocab_size": 120832,
  "num_nextn_predict_layers": 1,
  "quantization_config": {
    "quant_method": "compressed-tensors",
    "format": "nvfp4-pack-quantized",
    "config_groups": {
      "group_0": {
        "targets": [
          "re:.*\\.experts\\.\\d+\\..*",
          "re:.*model\\.layers\\.\\d+\\.mlp\\.experts\\.\\d+\\.gate_up_proj$"
        ],
        "weights": {
          "num_bits": 4,
          "type": "float",
          "strategy": "tensor_group",
          "group_size": 16,
          "symmetric": true
        }
      }
    },
    "ignore": [
      "re:.*lm_head$",
      "re:.*model\\.embed_tokens$",
      "re:.*model\\.layers\\.\\d+\\.mlp\\.down_proj$",
      "re:.*model\\.layers\\.\\d+\\.mlp\\.gate_proj$",
      "re:.*model\\.layers\\.\\d+\\.mlp\\.up_proj$",
      "re:.*model\\.layers\\.\\d+\\.self_attn\\.k_proj$",
      "re:.*model\\.layers\\.\\d+\\.self_attn\\.o_proj$",
      "re:.*model\\.layers\\.\\d+\\.self_attn\\.q_proj$",
      "re:.*model\\.layers\\.\\d+\\.self_attn\\.v_proj$",
      "re:.*model\\.layers\\.\\d+\\.mlp\\.router\\.gate$",
      "re:.*model\\.layers\\.\\d+\\.mlp\\.shared_mlp\\.down_proj$",
      "re:.*model\\.layers\\.\\d+\\.mlp\\.shared_mlp\\.gate_proj$",
      "re:.*model\\.layers\\.\\d+\\.mlp\\.shared_mlp\\.up_proj$",
      "re:.*model\\.layers\\.\\d+\\.eh_proj$"
    ]
  }
}