config.json

{
  "_name_or_path": "ibm_granite/granite-vision-3.3-2b",
  "adapter_path": null,
    "auto_map": {
        "AutoModel": "modeling_granite_vision_embedding.GraniteVisionEmb",
        "AutoProcessor": "processing_granite_vision_embedding.GraniteVisionEmbProcessor",
        "AutoConfig":    "granite_vision_embedding_config.GraniteVisionEmbConfig"
    },
  "architectures": [
    "GraniteVisionEmb"
  ],
  "base_image_feature_location": "last",
  "base_model": null,
  "emb_dim_doc": 128,
  "emb_dim_query": 128,
  "image_grid_pinpoints": [
    [
      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": 49155,
  "model_type": "granitevisionemb",
  "multimodal_projector_bias": true,
  "pretrained_language_model": "",
  "pretrained_vision_tower": "",
  "projector_hidden_act": "gelu",
  "text_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "ibm-granite/granite-3.1-2b-instruct",
    "architectures": [
      "GraniteForCausalLM"
    ],
    "attention_dropout": 0.1,
    "attention_multiplier": 0.015625,
    "bos_token_id": 0,
    "embedding_multiplier": 12.0,
    "eos_token_id": 0,
    "hidden_size": 2048,
    "intermediate_size": 8192,
    "logits_scaling": 8.0,
    "max_position_embeddings": 131072,
    "model_type": "granite",
    "num_hidden_layers": 40,
    "num_key_value_heads": 8,
    "pad_token_id": 0,
    "residual_multiplier": 0.22,
    "rms_norm_eps": 1e-05,
    "rope_theta": 300000,
    "tie_word_embeddings": true,
    "torch_dtype": "bfloat16",
    "vocab_size": 49156
  },
  "tie_word_embeddings": true,
  "torch_dtype": "float32",
  "transformers_version": "4.49.0",
  "use_image_newline_parameter": true,
  "vision_config": {
    "_attn_implementation_autoset": true,
    "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_hidden_layers": 27,
    "patch_size": 14,
    "torch_dtype": "bfloat16"
  },
  "vision_feature_layer": [
    -24,
    -20,
    -12,
    -1
  ],
  "vision_feature_select_strategy": "full"
}