{
  "architectures": [
    "VisionEncoderDecoderModel"
  ],
  "decoder": {
    "_name_or_path": "",
    "activation_dropout": 0.0,
    "activation_function": "relu",
    "add_cross_attention": true,
    "architectures": null,
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "bos_token_id": 0,
    "chunk_size_feed_forward": 0,
    "classifier_dropout": 0.0,
    "cross_attention_hidden_size": null,
    "d_model": 1024,
    "decoder_attention_heads": 16,
    "decoder_ffn_dim": 4096,
    "decoder_layerdrop": 0.0,
    "decoder_layers": 12,
    "decoder_start_token_id": 2,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "dropout": 0.1,
    "early_stopping": false,
    "encoder_hidden_size": 1024,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 2,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "init_std": 0.02,
    "is_decoder": true,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layernorm_embedding": false,
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 1024,
    "min_length": 0,
    "model_type": "trocr",
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": 1,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "scale_embedding": true,
    "sep_token_id": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": false,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "transformers_version": "4.12.0.dev0",
    "use_bfloat16": false,
    "use_cache": false,
    "use_learned_position_embeddings": false,
    "vocab_size": 50265
  },
  "encoder": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "attention_probs_dropout_prob": 0.0,
    "bad_words_ids": null,
    "bos_token_id": null,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "hidden_act": "gelu",
    "hidden_dropout_prob": 0.0,
    "hidden_size": 1024,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "image_size": 384,
    "initializer_range": 0.02,
    "intermediate_size": 4096,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "layer_norm_eps": 1e-12,
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "vit",
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 16,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_size": 16,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "qkv_bias": false,
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "transformers_version": "4.12.0.dev0",
    "use_bfloat16": false
  },
  "is_encoder_decoder": true,
  "model_type": "vision-encoder-decoder",
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": null
}