SmartPy/handwritten-text-recognition

1{2  "_name_or_path": "SmartPy/handwritten-text-recognition",3  "architectures": [4    "VisionEncoderDecoderModel"5  ],6  "decoder": {7    "_name_or_path": "bert-base-cased",8    "add_cross_attention": true,9    "architectures": [10      "BertForMaskedLM"11    ],12    "attention_probs_dropout_prob": 0.1,13    "bad_words_ids": null,14    "bos_token_id": null,15    "chunk_size_feed_forward": 0,16    "classifier_dropout": null,17    "cross_attention_hidden_size": null,18    "decoder_start_token_id": null,19    "diversity_penalty": 0.0,20    "do_sample": false,21    "early_stopping": false,22    "encoder_no_repeat_ngram_size": 0,23    "eos_token_id": null,24    "exponential_decay_length_penalty": null,25    "finetuning_task": null,26    "forced_bos_token_id": null,27    "forced_eos_token_id": null,28    "gradient_checkpointing": false,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    "task_specific_params": null,70    "temperature": 1.0,71    "tie_encoder_decoder": false,72    "tie_word_embeddings": true,73    "tokenizer_class": null,74    "top_k": 50,75    "top_p": 1.0,76    "torch_dtype": null,77    "torchscript": false,78    "transformers_version": "4.20.1",79    "type_vocab_size": 2,80    "typical_p": 1.0,81    "use_bfloat16": false,82    "use_cache": true,83    "vocab_size": 2899684  },85  "decoder_start_token_id": 101,86  "early_stopping": true,87  "encoder": {88    "_name_or_path": "google/vit-base-patch16-224-in21k",89    "add_cross_attention": false,90    "architectures": [91      "ViTModel"92    ],93    "attention_probs_dropout_prob": 0.0,94    "bad_words_ids": null,95    "bos_token_id": null,96    "chunk_size_feed_forward": 0,97    "cross_attention_hidden_size": null,98    "decoder_start_token_id": null,99    "diversity_penalty": 0.0,100    "do_sample": false,101    "early_stopping": false,102    "encoder_no_repeat_ngram_size": 0,103    "encoder_stride": 16,104    "eos_token_id": null,105    "exponential_decay_length_penalty": null,106    "finetuning_task": null,107    "forced_bos_token_id": null,108    "forced_eos_token_id": null,109    "hidden_act": "gelu",110    "hidden_dropout_prob": 0.0,111    "hidden_size": 768,112    "id2label": {113      "0": "LABEL_0",114      "1": "LABEL_1"115    },116    "image_size": 224,117    "initializer_range": 0.02,118    "intermediate_size": 3072,119    "is_decoder": false,120    "is_encoder_decoder": false,121    "label2id": {122      "LABEL_0": 0,123      "LABEL_1": 1124    },125    "layer_norm_eps": 1e-12,126    "length_penalty": 1.0,127    "max_length": 20,128    "min_length": 0,129    "model_type": "vit",130    "no_repeat_ngram_size": 0,131    "num_attention_heads": 12,132    "num_beam_groups": 1,133    "num_beams": 1,134    "num_channels": 3,135    "num_hidden_layers": 12,136    "num_return_sequences": 1,137    "output_attentions": false,138    "output_hidden_states": false,139    "output_scores": false,140    "pad_token_id": null,141    "patch_size": 16,142    "prefix": null,143    "problem_type": null,144    "pruned_heads": {},145    "qkv_bias": true,146    "remove_invalid_values": false,147    "repetition_penalty": 1.0,148    "return_dict": true,149    "return_dict_in_generate": false,150    "sep_token_id": null,151    "task_specific_params": null,152    "temperature": 1.0,153    "tie_encoder_decoder": false,154    "tie_word_embeddings": true,155    "tokenizer_class": null,156    "top_k": 50,157    "top_p": 1.0,158    "torch_dtype": null,159    "torchscript": false,160    "transformers_version": "4.20.1",161    "typical_p": 1.0,162    "use_bfloat16": false163  },164  "eos_token_id": 102,165  "is_encoder_decoder": true,166  "length_penalty": 2.0,167  "max_length": 150,168  "min_length": 56,169  "model_type": "vision-encoder-decoder",170  "no_repeat_ngram_size": 3,171  "num_beams": 4,172  "pad_token_id": 0,173  "tie_word_embeddings": false,174  "torch_dtype": "float32",175  "transformers_version": null,176  "vocab_size": 28996177}178