config.json

{
  "architectures": [
    "Granite4VisionForConditionalGeneration"
  ],
  "auto_map": {
    "AutoConfig": "configuration.Granite4VisionConfig",
    "AutoModel": "modeling.Granite4VisionForConditionalGeneration",
    "AutoModelForVision2Seq": "modeling.Granite4VisionForConditionalGeneration",
    "AutoModelForImageTextToText": "modeling.Granite4VisionForConditionalGeneration",
    "AutoProcessor": "processing.Granite4VisionProcessor"
  },
  "spatial_target_layers": [
    12,
    15,
    18,
    21
  ],
  "spatial_stride": 2,
  "spatial_vision_layer": -1,
  "downsample_rate": "4/8",
  "dtype": "bfloat16",
  "image_grid_pinpoints": [
    [
      384,
      384
    ],
    [
      384,
      768
    ],
    [
      384,
      1152
    ],
    [
      384,
      1536
    ],
    [
      384,
      1920
    ],
    [
      384,
      2304
    ],
    [
      384,
      2688
    ],
    [
      384,
      3072
    ],
    [
      384,
      3456
    ],
    [
      384,
      3840
    ],
    [
      768,
      384
    ],
    [
      768,
      768
    ],
    [
      768,
      1152
    ],
    [
      768,
      1536
    ],
    [
      768,
      1920
    ],
    [
      1152,
      384
    ],
    [
      1152,
      768
    ],
    [
      1152,
      1152
    ],
    [
      1536,
      384
    ],
    [
      1536,
      768
    ],
    [
      1920,
      384
    ],
    [
      1920,
      768
    ],
    [
      2304,
      384
    ],
    [
      2688,
      384
    ],
    [
      3072,
      384
    ],
    [
      3456,
      384
    ],
    [
      3840,
      384
    ]
  ],
  "image_seq_length": 576,
  "image_token_index": 100352,
  "initializer_range": 0.02,
  "model_type": "granite4_vision",
  "projector_dropout": 0.1,
  "projector_hidden_act": "gelu",
  "text_config": {
    "architectures": [
      "GraniteForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attention_multiplier": 0.015625,
    "bos_token_id": 100257,
    "embedding_multiplier": 12.0,
    "eos_token_id": 100257,
    "hidden_act": "silu",
    "hidden_size": 2560,
    "initializer_range": 0.1,
    "intermediate_size": 8192,
    "logits_scaling": 10.0,
    "max_position_embeddings": 131072,
    "mlp_bias": false,
    "model_type": "granite",
    "num_attention_heads": 40,
    "num_hidden_layers": 40,
    "num_key_value_heads": 8,
    "pad_token_id": 100256,
    "residual_multiplier": 0.22,
    "rms_norm_eps": 1e-05,
    "rope_scaling": null,
    "rope_theta": 10000000,
    "tie_word_embeddings": true,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.53.3",
    "use_cache": true,
    "vocab_size": 100353
  },
  "tie_word_embeddings": true,
  "transformers_version": "4.57.3",
  "use_spatial_sampling": true,
  "use_image_newline_parameter": true,
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "image_size": 384,
    "intermediate_size": 4304,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 27,
    "patch_size": 16
  },
  "vision_feature_select_strategy": "full",
  "deepstack_layer_map": [
    [
      -19,
      9
    ],
    [
      -13,
      6
    ],
    [
      -7,
      3
    ],
    [
      -1,
      0
    ]
  ]
}