Commit
·
38ab408
1
Parent(s):
5554857
add tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +2 -1
- vocab.txt +0 -0
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -2,7 +2,8 @@
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
4 |
"do_basic_tokenize": true,
|
5 |
-
"
|
|
|
6 |
"mask_token": "[MASK]",
|
7 |
"max_len": 512,
|
8 |
"model_max_length": 512,
|
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
"cls_token": "[CLS]",
|
4 |
"do_basic_tokenize": true,
|
5 |
+
"do_lower": true,
|
6 |
+
"do_lower_case": true,
|
7 |
"mask_token": "[MASK]",
|
8 |
"max_len": 512,
|
9 |
"model_max_length": 512,
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|