{
  "model_file": "model.safetensors",
  "model_file_bytes": 15656878852,
  "model_file_sha256": "4475b48270e4d2072886f084442e29f5e5eb16c7668d5a2a28404428e9c0b247",
  "total_tensor_count": 35923,
  "weight_packed_tensor_count": 11725,
  "weight_scale_tensor_count": 11725,
  "weight_scale_nonfinite_tensor_count": 0,
  "weight_scale_nonfinite_value_count": 0,
  "packed_exclusion_counts": {
    "vision_tower": 0,
    "router": 0,
    "token_embedding": 0,
    "vision_embedding": 0,
    "lm_head": 0
  },
  "representative_excluded_weight_dtypes": {
    "token_embedding": "bfloat16",
    "vision_projection": "bfloat16",
    "router": "bfloat16",
    "vision_mlp": "bfloat16"
  },
  "separate_lm_head_tensor_present": false,
  "quantization_config": {
    "config_groups": {
      "group_0": {
        "format": "pack-quantized",
        "input_activations": null,
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": "static",
          "block_structure": null,
          "dynamic": false,
          "group_size": 64,
          "num_bits": 4,
          "observer": "memoryless_minmax",
          "observer_kwargs": {},
          "scale_dtype": null,
          "strategy": "group",
          "symmetric": true,
          "type": "int",
          "zp_dtype": null
        }
      }
    },
    "format": "pack-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "model.vision_tower.patch_embedder.input_proj",
      "model.vision_tower.encoder.layers.0.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.0.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.0.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.0.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.0.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.0.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.0.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.1.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.1.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.1.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.1.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.1.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.1.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.1.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.2.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.2.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.2.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.2.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.2.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.2.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.2.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.3.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.3.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.3.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.3.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.3.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.3.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.3.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.4.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.4.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.4.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.4.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.4.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.4.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.4.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.5.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.5.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.5.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.5.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.5.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.5.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.5.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.6.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.6.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.6.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.6.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.6.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.6.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.6.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.7.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.7.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.7.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.7.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.7.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.7.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.7.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.8.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.8.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.8.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.8.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.8.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.8.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.8.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.9.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.9.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.9.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.9.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.9.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.9.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.9.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.10.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.10.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.10.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.10.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.10.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.10.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.10.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.11.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.11.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.11.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.11.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.11.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.11.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.11.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.12.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.12.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.12.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.12.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.12.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.12.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.12.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.13.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.13.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.13.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.13.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.13.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.13.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.13.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.14.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.14.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.14.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.14.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.14.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.14.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.14.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.15.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.15.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.15.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.15.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.15.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.15.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.15.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.16.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.16.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.16.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.16.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.16.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.16.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.16.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.17.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.17.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.17.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.17.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.17.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.17.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.17.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.18.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.18.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.18.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.18.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.18.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.18.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.18.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.19.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.19.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.19.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.19.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.19.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.19.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.19.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.20.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.20.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.20.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.20.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.20.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.20.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.20.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.21.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.21.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.21.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.21.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.21.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.21.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.21.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.22.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.22.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.22.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.22.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.22.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.22.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.22.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.23.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.23.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.23.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.23.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.23.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.23.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.23.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.24.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.24.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.24.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.24.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.24.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.24.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.24.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.25.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.25.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.25.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.25.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.25.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.25.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.25.mlp.down_proj.linear",
      "model.vision_tower.encoder.layers.26.self_attn.q_proj.linear",
      "model.vision_tower.encoder.layers.26.self_attn.k_proj.linear",
      "model.vision_tower.encoder.layers.26.self_attn.v_proj.linear",
      "model.vision_tower.encoder.layers.26.self_attn.o_proj.linear",
      "model.vision_tower.encoder.layers.26.mlp.gate_proj.linear",
      "model.vision_tower.encoder.layers.26.mlp.up_proj.linear",
      "model.vision_tower.encoder.layers.26.mlp.down_proj.linear",
      "model.language_model.layers.0.router",
      "model.language_model.layers.0.router.proj",
      "model.language_model.layers.1.router",
      "model.language_model.layers.1.router.proj",
      "model.language_model.layers.2.router",
      "model.language_model.layers.2.router.proj",
      "model.language_model.layers.3.router",
      "model.language_model.layers.3.router.proj",
      "model.language_model.layers.4.router",
      "model.language_model.layers.4.router.proj",
      "model.language_model.layers.5.router",
      "model.language_model.layers.5.router.proj",
      "model.language_model.layers.6.router",
      "model.language_model.layers.6.router.proj",
      "model.language_model.layers.7.router",
      "model.language_model.layers.7.router.proj",
      "model.language_model.layers.8.router",
      "model.language_model.layers.8.router.proj",
      "model.language_model.layers.9.router",
      "model.language_model.layers.9.router.proj",
      "model.language_model.layers.10.router",
      "model.language_model.layers.10.router.proj",
      "model.language_model.layers.11.router",
      "model.language_model.layers.11.router.proj",
      "model.language_model.layers.12.router",
      "model.language_model.layers.12.router.proj",
      "model.language_model.layers.13.router",
      "model.language_model.layers.13.router.proj",
      "model.language_model.layers.14.router",
      "model.language_model.layers.14.router.proj",
      "model.language_model.layers.15.router",
      "model.language_model.layers.15.router.proj",
      "model.language_model.layers.16.router",
      "model.language_model.layers.16.router.proj",
      "model.language_model.layers.17.router",
      "model.language_model.layers.17.router.proj",
      "model.language_model.layers.18.router",
      "model.language_model.layers.18.router.proj",
      "model.language_model.layers.19.router",
      "model.language_model.layers.19.router.proj",
      "model.language_model.layers.20.router",
      "model.language_model.layers.20.router.proj",
      "model.language_model.layers.21.router",
      "model.language_model.layers.21.router.proj",
      "model.language_model.layers.22.router",
      "model.language_model.layers.22.router.proj",
      "model.language_model.layers.23.router",
      "model.language_model.layers.23.router.proj",
      "model.language_model.layers.24.router",
      "model.language_model.layers.24.router.proj",
      "model.language_model.layers.25.router",
      "model.language_model.layers.25.router.proj",
      "model.language_model.layers.26.router",
      "model.language_model.layers.26.router.proj",
      "model.language_model.layers.27.router",
      "model.language_model.layers.27.router.proj",
      "model.language_model.layers.28.router",
      "model.language_model.layers.28.router.proj",
      "model.language_model.layers.29.router",
      "model.language_model.layers.29.router.proj",
      "model.embed_vision.embedding_projection",
      "lm_head"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.18.0"
  }
}