{
  "architectures": [
    "Pix2StructForConditionalGeneration"
  ],
  "bos_token_id": 0,
  "decoder_start_token_id": 0,
  "eos_token_id": 1,
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "is_encoder_decoder": true,
  "is_vqa": false,
  "model_type": "pix2struct",
  "pad_token_id": 0,
  "projection_dim": 64,
  "text_config": {
    "attention_dropout": 0.1,
    "bos_token_id": 0,
    "d_kv": 3,
    "dropout": 0.1,
    "hidden_size": 12,
    "initializer_range": 0.02,
    "intermediate_size": 37,
    "max_position_embeddings": 512,
    "model_type": "pix2struct_text_model",
    "num_heads": 4,
    "num_layers": 2,
    "projection_dim": 32,
    "vocab_size": 1305
  },
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.36.0.dev0",
  "vision_config": {
    "attention_dropout": 0.1,
    "dropout": 0.1,
    "hidden_size": 12,
    "image_size": 30,
    "initializer_range": 0.02,
    "intermediate_size": 37,
    "model_type": "pix2struct_vision_model",
    "num_attention_heads": 4,
    "num_channels": 3,
    "num_hidden_layers": 2,
    "patch_embed_hidden_size": 12,
    "patch_size": 2,
    "projection_dim": 32
  }
}