v2 update

This commit is contained in:
Lysandre 2021-09-15 17:27:40 -04:00
parent 57296f1cf0
commit 76879eecbb
5 changed files with 30532 additions and 0 deletions

7
preprocessor_config.json Normal file
View File

@ -0,0 +1,7 @@
{
"apply_ocr": true,
"do_resize": true,
"feature_extractor_type": "LayoutLMv2FeatureExtractor",
"resample": 2,
"size": 224
}

1
special_tokens_map.json Normal file
View File

@ -0,0 +1 @@
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

1
tokenizer.json Normal file

File diff suppressed because one or more lines are too long

1
tokenizer_config.json Normal file
View File

@ -0,0 +1 @@
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "cls_token_box": [0, 0, 0, 0], "sep_token_box": [1000, 1000, 1000, 1000], "pad_token_box": [0, 0, 0, 0], "pad_token_label": -100, "only_label_first_subword": true, "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "microsoft/layoutlmv2-base-uncased", "do_basic_tokenize": true, "never_split": null, "additional_special_tokens": null, "tokenizer_class": "LayoutLMv2Tokenizer"}

30522
vocab.txt Normal file

File diff suppressed because it is too large Load Diff