add tokenizer

This commit is contained in:
xhyi 2022-07-22 11:52:54 -07:00
parent 519f37fd49
commit a0efbb32b5
No known key found for this signature in database
GPG Key ID: E6BB1BF2F869ECC9
5 changed files with 150495 additions and 0 deletions

50001
merges.txt Normal file

File diff suppressed because it is too large Load Diff

51
special_tokens_map.json Normal file
View File

@ -0,0 +1,51 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"cls_token": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"mask_token": {
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sep_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

100355
tokenizer.json Normal file

File diff suppressed because it is too large Load Diff

87
tokenizer_config.json Normal file
View File

@ -0,0 +1,87 @@
{
"add_prefix_space": true,
"apply_ocr": true,
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"cls_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"cls_token_box": [
0,
0,
0,
0
],
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"name_or_path": "/home/xdrie/Downloads/layoutlmv3_docvqa_t11c5000/",
"only_label_first_subword": true,
"pad_token": {
"__type": "AddedToken",
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token_box": [
0,
0,
0,
0
],
"pad_token_label": -100,
"processor_class": "LayoutLMv3Processor",
"sep_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sep_token_box": [
0,
0,
0,
0
],
"special_tokens_map_file": null,
"tokenizer_class": "LayoutLMv3Tokenizer",
"trim_offsets": true,
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

1
vocab.json Normal file

File diff suppressed because one or more lines are too long