Sans1807/working
09
1{2 "_name_or_path": "Sans1807/content",3 "architectures": [4 "VisionEncoderDecoderModel"5 ],6 "decoder": {7 "_name_or_path": "",8 "activation_dropout": 0.0,9 "activation_function": "gelu",10 "add_cross_attention": true,11 "architectures": null,12 "attention_dropout": 0.0,13 "bad_words_ids": null,14 "begin_suppress_tokens": null,15 "bos_token_id": 0,16 "chunk_size_feed_forward": 0,17 "classifier_dropout": 0.0,18 "cross_attention_hidden_size": 768,19 "d_model": 1024,20 "decoder_attention_heads": 16,21 "decoder_ffn_dim": 4096,22 "decoder_layerdrop": 0.0,23 "decoder_layers": 12,24 "decoder_start_token_id": 2,25 "diversity_penalty": 0.0,26 "do_sample": false,27 "dropout": 0.1,28 "early_stopping": false,29 "encoder_no_repeat_ngram_size": 0,30 "eos_token_id": 2,31 "exponential_decay_length_penalty": null,32 "finetuning_task": null,33 "forced_bos_token_id": null,34 "forced_eos_token_id": null,35 "id2label": {36 "0": "LABEL_0",37 "1": "LABEL_1"38 },39 "init_std": 0.02,40 "is_decoder": true,41 "is_encoder_decoder": false,42 "label2id": {43 "LABEL_0": 0,44 "LABEL_1": 145 },46 "layernorm_embedding": true,47 "length_penalty": 1.0,48 "max_length": 20,49 "max_position_embeddings": 512,50 "min_length": 0,51 "model_type": "trocr",52 "no_repeat_ngram_size": 0,53 "num_beam_groups": 1,54 "num_beams": 1,55 "num_return_sequences": 1,56 "output_attentions": false,57 "output_hidden_states": false,58 "output_scores": false,59 "pad_token_id": 1,60 "prefix": null,61 "problem_type": null,62 "pruned_heads": {},63 "remove_invalid_values": false,64 "repetition_penalty": 1.0,65 "return_dict": true,66 "return_dict_in_generate": false,67 "scale_embedding": 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": null,79 "torchscript": false,80 "typical_p": 1.0,81 "use_bfloat16": false,82 "use_cache": false,83 "use_learned_position_embeddings": true,84 "vocab_size": 5026585 },86 "decoder_start_token_id": 0,87 "dropout": 0.1,88 "early_stopping": true,89 "encoder": {90 "_name_or_path": "",91 "add_cross_attention": false,92 "architectures": null,93 "attention_probs_dropout_prob": 0.0,94 "bad_words_ids": null,95 "begin_suppress_tokens": null,96 "bos_token_id": null,97 "chunk_size_feed_forward": 0,98 "cross_attention_hidden_size": null,99 "decoder_start_token_id": null,100 "diversity_penalty": 0.0,101 "do_sample": false,102 "early_stopping": false,103 "encoder_no_repeat_ngram_size": 0,104 "encoder_stride": 16,105 "eos_token_id": null,106 "exponential_decay_length_penalty": null,107 "finetuning_task": null,108 "forced_bos_token_id": null,109 "forced_eos_token_id": null,110 "hidden_act": "gelu",111 "hidden_dropout_prob": 0.0,112 "hidden_size": 768,113 "id2label": {114 "0": "LABEL_0",115 "1": "LABEL_1"116 },117 "image_size": 384,118 "initializer_range": 0.02,119 "intermediate_size": 3072,120 "is_decoder": false,121 "is_encoder_decoder": false,122 "label2id": {123 "LABEL_0": 0,124 "LABEL_1": 1125 },126 "layer_norm_eps": 1e-12,127 "length_penalty": 1.0,128 "max_length": 20,129 "min_length": 0,130 "model_type": "vit",131 "no_repeat_ngram_size": 0,132 "num_attention_heads": 12,133 "num_beam_groups": 1,134 "num_beams": 1,135 "num_channels": 3,136 "num_hidden_layers": 12,137 "num_return_sequences": 1,138 "output_attentions": false,139 "output_hidden_states": false,140 "output_scores": false,141 "pad_token_id": null,142 "patch_size": 16,143 "prefix": null,144 "problem_type": null,145 "pruned_heads": {},146 "qkv_bias": false,147 "remove_invalid_values": false,148 "repetition_penalty": 1.0,149 "return_dict": true,150 "return_dict_in_generate": false,151 "sep_token_id": null,152 "suppress_tokens": null,153 "task_specific_params": null,154 "temperature": 1.0,155 "tf_legacy_loss": false,156 "tie_encoder_decoder": false,157 "tie_word_embeddings": true,158 "tokenizer_class": null,159 "top_k": 50,160 "top_p": 1.0,161 "torch_dtype": null,162 "torchscript": false,163 "typical_p": 1.0,164 "use_bfloat16": false165 },166 "eos_token_id": 2,167 "is_encoder_decoder": true,168 "length_penalty": 2.0,169 "max_length": 64,170 "model_type": "vision-encoder-decoder",171 "no_repeat_ngram_size": 3,172 "num_beams": 4,173 "pad_token_id": 1,174 "tie_word_embeddings": false,175 "torch_dtype": "float32",176 "transformers_version": "4.44.2",177 "vocab_size": 50265178}179 