{
  "architectures": [
    "VisionEncoderDecoderModel"
  ],
  "decoder": {
    "_name_or_path": "prajjwal1/bert-tiny",
    "add_cross_attention": true,
    "attention_probs_dropout_prob": 0.1,
    "classifier_dropout": null,
    "dtype": "float32",
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.1,
    "hidden_size": 128,
    "initializer_range": 0.02,
    "intermediate_size": 512,
    "is_decoder": true,
    "layer_norm_eps": 1e-12,
    "max_position_embeddings": 512,
    "model_type": "bert",
    "num_attention_heads": 2,
    "num_hidden_layers": 2,
    "position_embedding_type": "absolute",
    "type_vocab_size": 2,
    "use_cache": true,
    "vocab_size": 30522
  },
  "decoder_start_token_id": 101,
  "dtype": "float32",
  "early_stopping": null,
  "encoder": {
    "_name_or_path": "google/vit-base-patch16-224-in21k",
    "architectures": [
      "ViTModel"
    ],
    "attention_probs_dropout_prob": 0.0,
    "dtype": "float32",
    "encoder_stride": 16,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.0,
    "hidden_size": 768,
    "image_size": 224,
    "initializer_range": 0.02,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-12,
    "model_type": "vit",
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "patch_size": 16,
    "pooler_act": "tanh",
    "pooler_output_size": 768,
    "qkv_bias": true
  },
  "eos_token_id": 102,
  "is_encoder_decoder": true,
  "length_penalty": null,
  "max_length": null,
  "model_type": "vision-encoder-decoder",
  "no_repeat_ngram_size": null,
  "num_beams": null,
  "pad_token_id": 0,
  "tie_word_embeddings": false,
  "transformers_version": "4.56.0",
  "vocab_size": 30522
}