Upload tokenizer
Browse files- tokenizer_config.json +2 -4
- vocab.txt +0 -0
tokenizer_config.json
CHANGED
@@ -44,17 +44,15 @@
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_basic_tokenize": true,
|
47 |
-
"do_lower_case":
|
48 |
"extra_special_tokens": {},
|
49 |
"mask_token": "[MASK]",
|
50 |
-
"
|
51 |
-
"model_max_length": 512,
|
52 |
"never_split": null,
|
53 |
"pad_token": "[PAD]",
|
54 |
"sep_token": "[SEP]",
|
55 |
"strip_accents": null,
|
56 |
"tokenize_chinese_chars": true,
|
57 |
"tokenizer_class": "BertTokenizer",
|
58 |
-
"truncation": true,
|
59 |
"unk_token": "[UNK]"
|
60 |
}
|
|
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
"extra_special_tokens": {},
|
49 |
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 1000000000000000019884624838656,
|
|
|
51 |
"never_split": null,
|
52 |
"pad_token": "[PAD]",
|
53 |
"sep_token": "[SEP]",
|
54 |
"strip_accents": null,
|
55 |
"tokenize_chinese_chars": true,
|
56 |
"tokenizer_class": "BertTokenizer",
|
|
|
57 |
"unk_token": "[UNK]"
|
58 |
}
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|