Commit
•
cdd847d
1
Parent(s):
6a163fd
Upload tokenizer
Browse files- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
| 3 |
"do_lower_case": true,
|
| 4 |
"mask_token": "[MASK]",
|
| 5 |
"model_max_length": 512,
|
| 6 |
"pad_token": "[PAD]",
|
| 7 |
"sep_token": "[SEP]",
|
| 8 |
-
"special_tokens_map_file": null,
|
| 9 |
"strip_accents": null,
|
| 10 |
"tokenize_chinese_chars": true,
|
| 11 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
| 1 |
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
"do_lower_case": true,
|
| 5 |
"mask_token": "[MASK]",
|
| 6 |
"model_max_length": 512,
|
| 7 |
"pad_token": "[PAD]",
|
| 8 |
"sep_token": "[SEP]",
|
|
|
|
| 9 |
"strip_accents": null,
|
| 10 |
"tokenize_chinese_chars": true,
|
| 11 |
"tokenizer_class": "BertTokenizer",
|