{
  "architectures": [
    "Blip3ModelForConditionalGeneration"
  ],
  "auto_map": {
    "AutoConfig": "configuration_blip_3.Blip3Config",
    "AutoModelForVision2Seq": "modeling_blip_3.Blip3ModelForConditionalGeneration"
  },
  "model_type": "blip_3",
  "text_config": {
    "initial_tokenizer_len": 32012,
    "model_type": "phi3",
    "sliding_window": 2047,
    "torch_dtype": "bfloat16"
  },
  "torch_dtype": "float32",
  "transformers_version": "4.41.0.dev0",
  "vision_encoder_config": {
    "anyres_patch_sampling": true,
    "image_aspect_ratio": "anyres",
    "model_type": "blip_3_vision_encoder"
  },
  "vision_tokenizer_config": {
    "model_type": "blip_3_vision_tokenizer"
  }
}