bombshelll/ViT_BioMedBert_ImageCaptioning_RadGenome
08
1{2 "_name_or_path": "/kaggle/working/ViT_BioMedBert_ImageCaptioning_RadGenome/model",3 "architectures": [4 "VisionEncoderDecoderModel"5 ],6 "decoder": {7 "_name_or_path": "bombshelll/BioMedBert-finetuned-RadGenome",8 "add_cross_attention": true,9 "architectures": [10 "BertLMHeadModel"11 ],12 "attention_probs_dropout_prob": 0.1,13 "bad_words_ids": null,14 "begin_suppress_tokens": null,15 "bos_token_id": 101,16 "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": 102,25 "exponential_decay_length_penalty": null,26 "finetuning_task": null,27 "forced_bos_token_id": null,28 "forced_eos_token_id": null,29 "hidden_act": "gelu",30 "hidden_dropout_prob": 0.1,31 "hidden_size": 768,32 "id2label": {33 "0": "LABEL_0",34 "1": "LABEL_1"35 },36 "initializer_range": 0.02,37 "intermediate_size": 3072,38 "is_decoder": true,39 "is_encoder_decoder": false,40 "label2id": {41 "LABEL_0": 0,42 "LABEL_1": 143 },44 "layer_norm_eps": 1e-12,45 "length_penalty": 1.0,46 "max_length": 20,47 "max_position_embeddings": 512,48 "min_length": 0,49 "model_type": "bert",50 "no_repeat_ngram_size": 0,51 "num_attention_heads": 12,52 "num_beam_groups": 1,53 "num_beams": 1,54 "num_hidden_layers": 12,55 "num_return_sequences": 1,56 "output_attentions": false,57 "output_hidden_states": false,58 "output_scores": false,59 "pad_token_id": 0,60 "position_embedding_type": "absolute",61 "prefix": null,62 "problem_type": null,63 "pruned_heads": {},64 "remove_invalid_values": false,65 "repetition_penalty": 1.0,66 "return_dict": true,67 "return_dict_in_generate": false,68 "sep_token_id": null,69 "suppress_tokens": null,70 "task_specific_params": null,71 "temperature": 1.0,72 "tf_legacy_loss": false,73 "tie_encoder_decoder": false,74 "tie_word_embeddings": true,75 "tokenizer_class": null,76 "top_k": 50,77 "top_p": 1.0,78 "torch_dtype": "float32",79 "torchscript": false,80 "type_vocab_size": 2,81 "typical_p": 1.0,82 "use_bfloat16": false,83 "use_cache": true,84 "vocab_size": 2889585 },86 "decoder_start_token_id": 2,87 "early_stopping": true,88 "encoder": {89 "_name_or_path": "google/vit-base-patch16-224-in21k",90 "add_cross_attention": false,91 "architectures": [92 "ViTModel"93 ],94 "attention_probs_dropout_prob": 0.0,95 "bad_words_ids": null,96 "begin_suppress_tokens": null,97 "bos_token_id": null,98 "chunk_size_feed_forward": 0,99 "cross_attention_hidden_size": null,100 "decoder_start_token_id": null,101 "diversity_penalty": 0.0,102 "do_sample": false,103 "early_stopping": false,104 "encoder_no_repeat_ngram_size": 0,105 "encoder_stride": 16,106 "eos_token_id": null,107 "exponential_decay_length_penalty": null,108 "finetuning_task": null,109 "forced_bos_token_id": null,110 "forced_eos_token_id": null,111 "hidden_act": "gelu",112 "hidden_dropout_prob": 0.0,113 "hidden_size": 768,114 "id2label": {115 "0": "LABEL_0",116 "1": "LABEL_1"117 },118 "image_size": 224,119 "initializer_range": 0.02,120 "intermediate_size": 3072,121 "is_decoder": false,122 "is_encoder_decoder": false,123 "label2id": {124 "LABEL_0": 0,125 "LABEL_1": 1126 },127 "layer_norm_eps": 1e-12,128 "length_penalty": 1.0,129 "max_length": 20,130 "min_length": 0,131 "model_type": "vit",132 "no_repeat_ngram_size": 0,133 "num_attention_heads": 12,134 "num_beam_groups": 1,135 "num_beams": 1,136 "num_channels": 3,137 "num_hidden_layers": 12,138 "num_return_sequences": 1,139 "output_attentions": false,140 "output_hidden_states": false,141 "output_scores": false,142 "pad_token_id": null,143 "patch_size": 16,144 "prefix": null,145 "problem_type": null,146 "pruned_heads": {},147 "qkv_bias": true,148 "remove_invalid_values": false,149 "repetition_penalty": 1.0,150 "return_dict": true,151 "return_dict_in_generate": false,152 "sep_token_id": null,153 "suppress_tokens": null,154 "task_specific_params": null,155 "temperature": 1.0,156 "tf_legacy_loss": false,157 "tie_encoder_decoder": false,158 "tie_word_embeddings": true,159 "tokenizer_class": null,160 "top_k": 50,161 "top_p": 1.0,162 "torch_dtype": null,163 "torchscript": false,164 "typical_p": 1.0,165 "use_bfloat16": false166 },167 "eos_token_id": 3,168 "is_encoder_decoder": true,169 "length_penalty": 2.0,170 "max_length": 80,171 "model_type": "vision-encoder-decoder",172 "no_repeat_ngram_size": 3,173 "num_beams": 4,174 "pad_token_id": 0,175 "tie_encoder_decoder": true,176 "tie_word_embeddings": false,177 "torch_dtype": "float32",178 "transformers_version": "4.44.0",179 "vocab_size": 28895180}181 