config.json

{
    "_commit_hash": null,
    "architectures": [
      "VisionEncoderDecoderModel"
    ],
    "decoder": {
      "_name_or_path": "DeepPavlov/rubert-base-cased",
      "add_cross_attention": true,
      "architectures": [
        "BertModel"
      ],
      "attention_probs_dropout_prob": 0.1,
      "bad_words_ids": null,
      "begin_suppress_tokens": null,
      "bos_token_id": null,
      "chunk_size_feed_forward": 0,
      "classifier_dropout": null,
      "cross_attention_hidden_size": null,
      "decoder_start_token_id": null,
      "directionality": "bidi",
      "diversity_penalty": 0.0,
      "do_sample": false,
      "early_stopping": false,
      "encoder_no_repeat_ngram_size": 0,
      "eos_token_id": null,
      "exponential_decay_length_penalty": null,
      "finetuning_task": null,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "hidden_act": "gelu",
      "hidden_dropout_prob": 0.1,
      "hidden_size": 768,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "initializer_range": 0.02,
      "intermediate_size": 3072,
      "is_decoder": true,
      "is_encoder_decoder": false,
      "label2id": {
        "LABEL_0": 0,
        "LABEL_1": 1
      },
      "layer_norm_eps": 1e-12,
      "length_penalty": 1.0,
      "max_length": 20,
      "max_position_embeddings": 512,
      "min_length": 0,
      "model_type": "bert",
      "no_repeat_ngram_size": 0,
      "num_attention_heads": 12,
      "num_beam_groups": 1,
      "num_beams": 1,
      "num_hidden_layers": 12,
      "num_return_sequences": 1,
      "output_attentions": false,
      "output_hidden_states": false,
      "output_past": true,
      "output_scores": false,
      "pad_token_id": 0,
      "pooler_fc_size": 768,
      "pooler_num_attention_heads": 12,
      "pooler_num_fc_layers": 3,
      "pooler_size_per_head": 128,
      "pooler_type": "first_token_transform",
      "position_embedding_type": "absolute",
      "prefix": null,
      "problem_type": null,
      "pruned_heads": {},
      "remove_invalid_values": false,
      "repetition_penalty": 1.0,
      "return_dict": true,
      "return_dict_in_generate": false,
      "sep_token_id": null,
      "suppress_tokens": null,
      "task_specific_params": null,
      "temperature": 1.0,
      "tf_legacy_loss": false,
      "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": "4.24.0",
      "type_vocab_size": 2,
      "typical_p": 1.0,
      "use_bfloat16": false,
      "use_cache": true,
      "vocab_size": 119547
    },
    "decoder_start_token_id": 101,
    "early_stopping": true,
    "encoder": {
      "_name_or_path": "google/vit-base-patch16-224-in21k",
      "add_cross_attention": false,
      "architectures": [
        "ViTModel"
      ],
      "attention_probs_dropout_prob": 0.0,
      "bad_words_ids": null,
      "begin_suppress_tokens": 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,
      "encoder_stride": 16,
      "eos_token_id": null,
      "exponential_decay_length_penalty": null,
      "finetuning_task": null,
      "forced_bos_token_id": null,
      "forced_eos_token_id": null,
      "hidden_act": "gelu",
      "hidden_dropout_prob": 0.0,
      "hidden_size": 768,
      "id2label": {
        "0": "LABEL_0",
        "1": "LABEL_1"
      },
      "image_size": 224,
      "initializer_range": 0.02,
      "intermediate_size": 3072,
      "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": 12,
      "num_beam_groups": 1,
      "num_beams": 1,
      "num_channels": 3,
      "num_hidden_layers": 12,
      "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": true,
      "remove_invalid_values": false,
      "repetition_penalty": 1.0,
      "return_dict": true,
      "return_dict_in_generate": false,
      "sep_token_id": null,
      "suppress_tokens": null,
      "task_specific_params": null,
      "temperature": 1.0,
      "tf_legacy_loss": false,
      "tie_encoder_decoder": false,
      "tie_word_embeddings": true,
      "tokenizer_class": "BertTokenizer",
      "top_k": 50,
      "top_p": 1.0,
      "torch_dtype": null,
      "torchscript": false,
      "transformers_version": "4.24.0",
      "typical_p": 1.0,
      "use_bfloat16": false
    },
    "eos_token_id": 102,
    "is_encoder_decoder": true,
    "length_penalty": 2.0,
    "max_length": 64,
    "model_type": "vision-encoder-decoder",
    "no_repeat_ngram_size": 3,
    "num_beams": 4,
    "pad_token_id": 0,
    "tie_word_embeddings": false,
    "torch_dtype": "float32",
    "transformers_version": null,
    "vocab_size": 119547
  }