{
    "architectures": [
        "Gemma4ForConditionalGeneration"
    ],
    "audio_config": null,
    "audio_token_id": 258881,
    "boa_token_id": 256000,
    "boi_token_id": 255999,
    "dtype": "bfloat16",
    "eoa_token_id": 258883,
    "eoa_token_index": 258883,
    "eoi_token_id": 258882,
    "eos_token_id": [
        1,
        106,
        50
    ],
    "image_token_id": 258880,
    "initializer_range": 0.02,
    "model_type": "gemma4",
    "quantization": {
        "group_size": 64,
        "bits": 4,
        "mode": "affine",
        "language_model.model.layers.0.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.0.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.0.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.0.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.1.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.1.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.1.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.1.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.2.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.2.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.2.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.2.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.3.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.3.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.3.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.3.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.4.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.4.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.4.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.4.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.5.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.5.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.5.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.5.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.6.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.6.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.6.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.6.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.7.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.7.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.7.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.7.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.8.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.8.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.8.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.8.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.9.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.9.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.9.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.9.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.10.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.10.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.10.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.10.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.11.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.11.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.11.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.11.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.12.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.12.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.12.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.12.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.13.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.13.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.13.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.13.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.14.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.14.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.14.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.14.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.15.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.15.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.15.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.15.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.16.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.16.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.16.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.16.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.17.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.17.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.17.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.17.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.18.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.18.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.18.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.18.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.19.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.19.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.19.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.19.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.20.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.20.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.20.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.20.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.21.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.21.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.21.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.21.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.22.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.22.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.22.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.22.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.23.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.23.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.23.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.23.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.24.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.24.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.24.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.24.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.25.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.25.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.25.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.25.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.26.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.26.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.26.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.26.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.27.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.27.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.27.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.27.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.28.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.28.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.28.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.28.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.29.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.29.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.29.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.29.router.proj": {
            "group_size": 64,
            "bits": 8
        }
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 4,
        "mode": "affine",
        "language_model.model.layers.0.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.0.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.0.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.0.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.1.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.1.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.1.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.1.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.2.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.2.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.2.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.2.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.3.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.3.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.3.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.3.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.4.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.4.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.4.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.4.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.5.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.5.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.5.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.5.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.6.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.6.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.6.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.6.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.7.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.7.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.7.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.7.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.8.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.8.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.8.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.8.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.9.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.9.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.9.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.9.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.10.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.10.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.10.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.10.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.11.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.11.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.11.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.11.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.12.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.12.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.12.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.12.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.13.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.13.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.13.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.13.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.14.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.14.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.14.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.14.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.15.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.15.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.15.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.15.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.16.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.16.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.16.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.16.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.17.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.17.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.17.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.17.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.18.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.18.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.18.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.18.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.19.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.19.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.19.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.19.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.20.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.20.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.20.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.20.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.21.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.21.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.21.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.21.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.22.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.22.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.22.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.22.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.23.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.23.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.23.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.23.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.24.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.24.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.24.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.24.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.25.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.25.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.25.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.25.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.26.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.26.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.26.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.26.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.27.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.27.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.27.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.27.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.28.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.28.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.28.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.28.router.proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.29.mlp.gate_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.29.mlp.down_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.29.mlp.up_proj": {
            "group_size": 64,
            "bits": 8
        },
        "language_model.model.layers.29.router.proj": {
            "group_size": 64,
            "bits": 8
        }
    },
    "text_config": {
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attention_k_eq_v": true,
        "bos_token_id": 2,
        "dtype": "bfloat16",
        "enable_moe_block": true,
        "eos_token_id": 1,
        "final_logit_softcapping": 30.0,
        "global_head_dim": 512,
        "head_dim": 256,
        "hidden_activation": "gelu_pytorch_tanh",
        "hidden_size": 2816,
        "hidden_size_per_layer_input": 0,
        "initializer_range": 0.02,
        "intermediate_size": 2112,
        "layer_types": [
            "sliding_attention",
            "sliding_attention",
            "sliding_attention",
            "sliding_attention",
            "sliding_attention",
            "full_attention",
            "sliding_attention",
            "sliding_attention",
            "sliding_attention",
            "sliding_attention",
            "sliding_attention",
            "full_attention",
            "sliding_attention",
            "sliding_attention",
            "sliding_attention",
            "sliding_attention",
            "sliding_attention",
            "full_attention",
            "sliding_attention",
            "sliding_attention",
            "sliding_attention",
            "sliding_attention",
            "sliding_attention",
            "full_attention",
            "sliding_attention",
            "sliding_attention",
            "sliding_attention",
            "sliding_attention",
            "sliding_attention",
            "full_attention"
        ],
        "max_position_embeddings": 262144,
        "model_type": "gemma4_text",
        "moe_intermediate_size": 704,
        "num_attention_heads": 16,
        "num_experts": 128,
        "num_global_key_value_heads": 2,
        "num_hidden_layers": 30,
        "num_key_value_heads": 8,
        "num_kv_shared_layers": 0,
        "pad_token_id": 0,
        "rms_norm_eps": 1e-06,
        "rope_parameters": {
            "full_attention": {
                "partial_rotary_factor": 0.25,
                "rope_theta": 1000000.0,
                "rope_type": "proportional"
            },
            "sliding_attention": {
                "rope_theta": 10000.0,
                "rope_type": "default"
            }
        },
        "sliding_window": 1024,
        "tie_word_embeddings": true,
        "top_k_experts": 8,
        "use_bidirectional_attention": "vision",
        "use_cache": true,
        "use_double_wide_mlp": false,
        "vocab_size": 262144,
        "vocab_size_per_layer_input": 262144
    },
    "tie_word_embeddings": true,
    "transformers_version": "5.5.0.dev0",
    "video_token_id": 258884,
    "vision_config": {
        "_name_or_path": "",
        "architectures": null,
        "attention_bias": false,
        "attention_dropout": 0.0,
        "chunk_size_feed_forward": 0,
        "default_output_length": 280,
        "dtype": "bfloat16",
        "global_head_dim": 72,
        "head_dim": 72,
        "hidden_activation": "gelu_pytorch_tanh",
        "hidden_size": 1152,
        "id2label": {
            "0": "LABEL_0",
            "1": "LABEL_1"
        },
        "initializer_range": 0.02,
        "intermediate_size": 4304,
        "is_encoder_decoder": false,
        "label2id": {
            "LABEL_0": 0,
            "LABEL_1": 1
        },
        "max_position_embeddings": 131072,
        "model_type": "gemma4_vision",
        "num_attention_heads": 16,
        "num_hidden_layers": 27,
        "num_key_value_heads": 16,
        "output_attentions": false,
        "output_hidden_states": false,
        "patch_size": 16,
        "pooling_kernel_size": 3,
        "position_embedding_size": 10240,
        "problem_type": null,
        "return_dict": true,
        "rms_norm_eps": 1e-06,
        "rope_parameters": {
            "rope_theta": 100.0,
            "rope_type": "default"
        },
        "standardize": true,
        "use_clipped_linears": false
    },
    "vision_soft_tokens_per_image": 280
}