config.json

{
  "architectures": [
    "VisionEncoderDecoderModel"
  ],
  "decoder": {
    "_name_or_path": "facebook/bart-base",
    "activation_dropout": 0.1,
    "activation_function": "gelu",
    "add_bias_logits": false,
    "add_cross_attention": true,
    "add_final_layer_norm": false,
    "architectures": [
      "BartModel"
    ],
    "attention_dropout": 0.1,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 0,
    "chunk_size_feed_forward": 0,
    "classif_dropout": 0.1,
    "classifier_dropout": 0.0,
    "cross_attention_hidden_size": null,
    "d_model": 768,
    "decoder_attention_heads": 12,
    "decoder_ffn_dim": 3072,
    "decoder_layerdrop": 0.0,
    "decoder_layers": 6,
    "decoder_start_token_id": 2,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "dropout": 0.1,
    "early_stopping": true,
    "encoder_attention_heads": 12,
    "encoder_ffn_dim": 3072,
    "encoder_layerdrop": 0.0,
    "encoder_layers": 6,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 2,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": 0,
    "forced_eos_token_id": 2,
    "gradient_checkpointing": false,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1",
      "2": "LABEL_2"
    },
    "init_std": 0.02,
    "is_decoder": true,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1,
      "LABEL_2": 2
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "max_position_embeddings": 1024,
    "min_length": 0,
    "model_type": "bart",
    "no_repeat_ngram_size": 3,
    "normalize_before": false,
    "normalize_embedding": true,
    "num_beam_groups": 1,
    "num_beams": 4,
    "num_hidden_layers": 6,
    "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": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": {
      "summarization": {
        "length_penalty": 1.0,
        "max_length": 128,
        "min_length": 12,
        "num_beams": 4
      },
      "summarization_cnn": {
        "length_penalty": 2.0,
        "max_length": 142,
        "min_length": 56,
        "num_beams": 4
      },
      "summarization_xsum": {
        "length_penalty": 1.0,
        "max_length": 62,
        "min_length": 11,
        "num_beams": 6
      }
    },
    "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": "float32",
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "vocab_size": 50265
  },
  "decoder_model_type": "BartForCausalLM",
  "decoder_start_token_id": 0,
  "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": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "typical_p": 1.0,
    "use_bfloat16": false
  },
  "eos_token_id": 2,
  "finetuned_from": "google/vit-base-patch16-224-in21k + facebook/bart-base",
  "is_encoder_decoder": true,
  "max_length": 128,
  "model_type": "vision-encoder-decoder",
  "pad_token_id": 1,
  "task": "Image Captioning",
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.44.2",
  "vision_model_type": "ViTModel"
}