{
  "architectures": [
    "Qwen3_5MoeForConditionalGeneration"
  ],
  "image_token_id": 248056,
  "model_type": "qwen3_5_moe",
  "text_config": {
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attn_output_gate": true,
    "dtype": "bfloat16",
    "eos_token_id": 248044,
    "full_attention_interval": 4,
    "head_dim": 256,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "layer_types": [
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention",
      "linear_attention",
      "linear_attention",
      "linear_attention",
      "full_attention"
    ],
    "linear_conv_kernel_dim": 4,
    "linear_key_head_dim": 128,
    "linear_num_key_heads": 16,
    "linear_num_value_heads": 32,
    "linear_value_head_dim": 128,
    "max_position_embeddings": 262144,
    "mlp_only_layers": [],
    "model_type": "qwen3_5_moe_text",
    "moe_intermediate_size": 512,
    "mtp_num_hidden_layers": 1,
    "mtp_use_dedicated_embeddings": false,
    "num_attention_heads": 16,
    "num_experts": 256,
    "num_experts_per_tok": 8,
    "num_hidden_layers": 40,
    "num_key_value_heads": 2,
    "rms_norm_eps": 1e-06,
    "router_aux_loss_coef": 0.001,
    "shared_expert_intermediate_size": 512,
    "use_cache": true,
    "vocab_size": 248320,
    "mamba_ssm_dtype": "float32",
    "rope_parameters": {
      "mrope_interleaved": true,
      "mrope_section": [
        11,
        11,
        10
      ],
      "rope_type": "default",
      "rope_theta": 10000000,
      "partial_rotary_factor": 0.25
    }
  },
  "tie_word_embeddings": false,
  "transformers_version": "4.57.0.dev0",
  "video_token_id": 248057,
  "vision_config": {
    "deepstack_visual_indexes": [],
    "depth": 27,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "in_channels": 3,
    "initializer_range": 0.02,
    "intermediate_size": 4304,
    "model_type": "qwen3_5_moe",
    "num_heads": 16,
    "num_position_embeddings": 2304,
    "out_hidden_size": 2048,
    "patch_size": 16,
    "spatial_merge_size": 2,
    "temporal_patch_size": 2
  },
  "vision_end_token_id": 248054,
  "vision_start_token_id": 248053,
  "quantization_config": {
    "bits": 4,
    "checkpoint_format": "gptq",
    "desc_act": false,
    "dynamic": {
      "-:.*linear_attn\\.in_proj_qkv": {},
      "-:.*linear_attn\\.in_proj_z": {},
      "-:.*linear_attn\\.out_proj": {},
      "-:.*shared_expert\\.down_proj": {},
      "-:.*shared_expert\\.gate_proj": {},
      "-:.*shared_expert\\.up_proj": {}
    },
    "format": "gptq",
    "group_size": 32,
    "lm_head": false,
    "meta": {
      "act_group_aware": true,
      "auto_forward_data_parallel": false,
      "damp_auto_increment": 0.01,
      "damp_percent": 0.05,
      "failsafe": {
        "smooth": {
          "group_size_threshold": 128,
          "k": 2.75,
          "type": "mad"
        },
        "strategy": "rtn",
        "threshold": "0.5%"
      },
      "gc_mode": "interval",
      "gptaq": null,
      "hessian": {
        "chunk_bytes": null,
        "chunk_size": null,
        "staging_dtype": "float32"
      },
      "mock_quantization": false,
      "mse": 0.0,
      "offload_to_disk": false,
      "offload_to_disk_path": null,
      "pack_impl": "cpu",
      "quantizer": [
        "gptqmodel:5.7.1"
      ],
      "static_groups": false,
      "true_sequential": true,
      "uri": "https://github.com/modelcloud/gptqmodel",
      "vram_strategy": "exclusive",
      "wait_for_submodule_finalizers": false
    },
    "pack_dtype": "int32",
    "quant_method": "gptq",
    "sym": true
  }
}