vikp/layout_segmenter
152.8k
1{2 "add_prefix_space": true,3 "added_tokens_decoder": {4 "0": {5 "content": "<s>",6 "lstrip": false,7 "normalized": false,8 "rstrip": false,9 "single_word": false,10 "special": true11 },12 "1": {13 "content": "<pad>",14 "lstrip": false,15 "normalized": false,16 "rstrip": false,17 "single_word": false,18 "special": true19 },20 "2": {21 "content": "</s>",22 "lstrip": false,23 "normalized": false,24 "rstrip": false,25 "single_word": false,26 "special": true27 },28 "3": {29 "content": "<unk>",30 "lstrip": false,31 "normalized": false,32 "rstrip": false,33 "single_word": false,34 "special": true35 },36 "50264": {37 "content": "<mask>",38 "lstrip": false,39 "normalized": false,40 "rstrip": false,41 "single_word": false,42 "special": true43 }44 },45 "additional_special_tokens": [46 "<s>",47 "<pad>",48 "</s>",49 "<unk>",50 "<mask>"51 ],52 "apply_ocr": false,53 "bos_token": "<s>",54 "clean_up_tokenization_spaces": true,55 "cls_token": "<s>",56 "cls_token_box": [57 0,58 0,59 0,60 061 ],62 "eos_token": "</s>",63 "errors": "replace",64 "mask_token": "<mask>",65 "model_max_length": 512,66 "only_label_first_subword": true,67 "pad_token": "<pad>",68 "pad_token_box": [69 0,70 0,71 0,72 073 ],74 "pad_token_label": -100,75 "processor_class": "LayoutLMv3Processor",76 "sep_token": "</s>",77 "sep_token_box": [78 0,79 0,80 0,81 082 ],83 "tokenizer_class": "LayoutLMv3Tokenizer",84 "trim_offsets": true,85 "unk_token": "<unk>"86}87 