{
  "architectures": [
    "Pix2SeqForConditionalGeneration"
  ],
  "attention_probs_dropout_prob": 0.0,
  "bos_token_id": 10,
  "dec_proj_mode": "mlp",
  "dim_decoder": 512,
  "drop_path_rate": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "image_size": 640,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "is_encoder_decoder": true,
  "layer_norm_eps": 1e-12,
  "max_position_embeddings": 512,
  "model_type": "pix2seq",
  "num_attention_heads_decoder": 16,
  "num_attention_heads_encoder": 12,
  "num_channels": 3,
  "num_decoder_layers": 6,
  "num_encoder_layers": 12,
  "output_bias": true,
  "patch_size": 16,
  "positional_encoding": "sin_cos",
  "positional_encoding_decoder": "learned",
  "qkv_bias": true,
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.19.0.dev0",
  "use_cache": true,
  "use_cls_token": false,
  "vocab_size": 3000
}