Commit
·
234eca4
1
Parent(s):
cb6b075
Upload tokenizer
Browse files- tokenizer_config.json +2 -1
tokenizer_config.json
CHANGED
|
@@ -1,11 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"clean_up_tokenization_spaces": true,
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
"do_lower_case": false,
|
| 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",
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
| 3 |
"do_lower_case": false,
|
| 4 |
"mask_token": "[MASK]",
|
| 5 |
"model_max_length": 512,
|
| 6 |
+
"name_or_path": "bert-base-cased",
|
| 7 |
"pad_token": "[PAD]",
|
| 8 |
"sep_token": "[SEP]",
|
| 9 |
+
"special_tokens_map_file": null,
|
| 10 |
"strip_accents": null,
|
| 11 |
"tokenize_chinese_chars": true,
|
| 12 |
"tokenizer_class": "BertTokenizer",
|