{
  "architectures": [
    "OmniModel"
  ],
  "audio_codebook_size": 1024,
  "audio_codebooks": 8,
  "audio_frame_size": 320,
  "auto_map": {
    "AutoConfig": "configuration_omni.OmniConfig",
    "AutoModel": "modeling_omni.OmniModel"
  },
  "checkpoint_format": "the-net-shared-aliases-v2",
  "context_dim": 256,
  "eeg_channels": 64,
  "head_dim": 128,
  "initialization": "constant, untrained",
  "model_type": "the_net_omni",
  "patch_size": 4,
  "stages": {
    "audio_decoder": [
      [
        4096,
        12,
        1,
        4,
        1
      ],
      [
        8192,
        84,
        8,
        2,
        2
      ]
    ],
    "audio_encoder": [
      [
        4096,
        12,
        1,
        4,
        1
      ],
      [
        8192,
        24,
        1,
        4,
        1
      ],
      [
        12288,
        12,
        1,
        4,
        1
      ]
    ],
    "eeg_encoder": [
      [
        2048,
        6,
        1,
        4,
        1
      ],
      [
        4096,
        12,
        1,
        4,
        1
      ],
      [
        8192,
        6,
        1,
        4,
        1
      ]
    ],
    "fusion": [
      [
        16384,
        30,
        8,
        3,
        2
      ]
    ],
    "image_decoder": [
      [
        4096,
        8,
        1,
        4,
        1
      ],
      [
        12288,
        52,
        16,
        2,
        2
      ]
    ],
    "image_encoder": [
      [
        4096,
        8,
        1,
        4,
        1
      ],
      [
        8192,
        24,
        1,
        4,
        1
      ],
      [
        12288,
        24,
        1,
        4,
        1
      ]
    ],
    "memory_control": [
      [
        8192,
        38,
        32,
        2,
        2
      ]
    ],
    "text_encoder": [
      [
        2048,
        6,
        1,
        4,
        1
      ],
      [
        4096,
        12,
        1,
        4,
        1
      ],
      [
        8192,
        6,
        1,
        4,
        1
      ]
    ],
    "video_decoder": [
      [
        8192,
        8,
        1,
        4,
        1
      ],
      [
        16384,
        88,
        16,
        2,
        2
      ]
    ],
    "video_encoder": [
      [
        4096,
        8,
        1,
        4,
        1
      ],
      [
        8192,
        32,
        1,
        4,
        1
      ],
      [
        16384,
        44,
        1,
        4,
        1
      ]
    ],
    "world_model": [
      [
        8192,
        48,
        128,
        2,
        2
      ],
      [
        12288,
        48,
        128,
        2,
        2
      ],
      [
        16384,
        34,
        128,
        2,
        2
      ]
    ]
  },
  "transformers_version": "4.57.6",
  "vocab_size": 259,
  "quantization_config": {
    "quant_method": "compressed-tensors",
    "format": "pack-quantized",
    "config_groups": {
      "shared_bank": {
        "targets": [
          "shared_bank"
        ],
        "weights": {
          "num_bits": 1,
          "type": "int",
          "symmetric": false,
          "strategy": "tensor",
          "dynamic": false
        }
      }
    }
  }
}