atasoglu/vit-bert-flickr8k

1{2  "_commit_hash": null,3  "architectures": [4    "VisionEncoderDecoderModel"5  ],6  "decoder": {7    "_name_or_path": "bert-base-uncased",8    "add_cross_attention": true,9    "architectures": [10      "BertForMaskedLM"11    ],12    "attention_probs_dropout_prob": 0.1,13    "bad_words_ids": null,14    "begin_suppress_tokens": null,15    "bos_token_id": null,16    "chunk_size_feed_forward": 0,17    "classifier_dropout": null,18    "cross_attention_hidden_size": null,19    "decoder_start_token_id": null,20    "diversity_penalty": 0.0,21    "do_sample": false,22    "early_stopping": false,23    "encoder_no_repeat_ngram_size": 0,24    "eos_token_id": null,25    "exponential_decay_length_penalty": null,26    "finetuning_task": null,27    "forced_bos_token_id": null,28    "forced_eos_token_id": null,29    "gradient_checkpointing": false,30    "hidden_act": "gelu",31    "hidden_dropout_prob": 0.1,32    "hidden_size": 768,33    "id2label": {34      "0": "LABEL_0",35      "1": "LABEL_1"36    },37    "initializer_range": 0.02,38    "intermediate_size": 3072,39    "is_decoder": true,40    "is_encoder_decoder": false,41    "label2id": {42      "LABEL_0": 0,43      "LABEL_1": 144    },45    "layer_norm_eps": 1e-12,46    "length_penalty": 1.0,47    "max_length": 20,48    "max_position_embeddings": 512,49    "min_length": 0,50    "model_type": "bert",51    "no_repeat_ngram_size": 0,52    "num_attention_heads": 12,53    "num_beam_groups": 1,54    "num_beams": 1,55    "num_hidden_layers": 12,56    "num_return_sequences": 1,57    "output_attentions": false,58    "output_hidden_states": false,59    "output_scores": false,60    "pad_token_id": 0,61    "position_embedding_type": "absolute",62    "prefix": null,63    "problem_type": null,64    "pruned_heads": {},65    "remove_invalid_values": false,66    "repetition_penalty": 1.0,67    "return_dict": true,68    "return_dict_in_generate": false,69    "sep_token_id": null,70    "suppress_tokens": null,71    "task_specific_params": null,72    "temperature": 1.0,73    "tf_legacy_loss": false,74    "tie_encoder_decoder": false,75    "tie_word_embeddings": true,76    "tokenizer_class": null,77    "top_k": 50,78    "top_p": 1.0,79    "torch_dtype": null,80    "torchscript": false,81    "transformers_version": "4.29.2",82    "type_vocab_size": 2,83    "typical_p": 1.0,84    "use_bfloat16": false,85    "use_cache": true,86    "vocab_size": 3052287  },88  "decoder_start_token_id": 101,89  "encoder": {90    "_name_or_path": "google/vit-base-patch16-224-in21k",91    "add_cross_attention": false,92    "architectures": [93      "ViTModel"94    ],95    "attention_probs_dropout_prob": 0.0,96    "bad_words_ids": null,97    "begin_suppress_tokens": null,98    "bos_token_id": null,99    "chunk_size_feed_forward": 0,100    "cross_attention_hidden_size": null,101    "decoder_start_token_id": null,102    "diversity_penalty": 0.0,103    "do_sample": false,104    "early_stopping": false,105    "encoder_no_repeat_ngram_size": 0,106    "encoder_stride": 16,107    "eos_token_id": null,108    "exponential_decay_length_penalty": null,109    "finetuning_task": null,110    "forced_bos_token_id": null,111    "forced_eos_token_id": null,112    "hidden_act": "gelu",113    "hidden_dropout_prob": 0.0,114    "hidden_size": 768,115    "id2label": {116      "0": "LABEL_0",117      "1": "LABEL_1"118    },119    "image_size": 224,120    "initializer_range": 0.02,121    "intermediate_size": 3072,122    "is_decoder": false,123    "is_encoder_decoder": false,124    "label2id": {125      "LABEL_0": 0,126      "LABEL_1": 1127    },128    "layer_norm_eps": 1e-12,129    "length_penalty": 1.0,130    "max_length": 20,131    "min_length": 0,132    "model_type": "vit",133    "no_repeat_ngram_size": 0,134    "num_attention_heads": 12,135    "num_beam_groups": 1,136    "num_beams": 1,137    "num_channels": 3,138    "num_hidden_layers": 12,139    "num_return_sequences": 1,140    "output_attentions": false,141    "output_hidden_states": false,142    "output_scores": false,143    "pad_token_id": null,144    "patch_size": 16,145    "prefix": null,146    "problem_type": null,147    "pruned_heads": {},148    "qkv_bias": true,149    "remove_invalid_values": false,150    "repetition_penalty": 1.0,151    "return_dict": true,152    "return_dict_in_generate": false,153    "sep_token_id": null,154    "suppress_tokens": null,155    "task_specific_params": null,156    "temperature": 1.0,157    "tf_legacy_loss": false,158    "tie_encoder_decoder": false,159    "tie_word_embeddings": true,160    "tokenizer_class": null,161    "top_k": 50,162    "top_p": 1.0,163    "torch_dtype": null,164    "torchscript": false,165    "transformers_version": "4.29.2",166    "typical_p": 1.0,167    "use_bfloat16": false168  },169  "is_encoder_decoder": true,170  "model_type": "vision-encoder-decoder",171  "pad_token_id": 0,172  "tie_word_embeddings": false,173  "torch_dtype": "float32",174  "transformers_version": null175}176