Commit
•
0d6cf2f
1
Parent(s):
f4053f4
Upload tokenizer
Browse files- tokenizer_config.json +3 -1
- vocab.txt +0 -0
tokenizer_config.json
CHANGED
|
@@ -43,9 +43,11 @@
|
|
| 43 |
},
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
-
"
|
|
|
|
| 47 |
"mask_token": "[MASK]",
|
| 48 |
"model_max_length": 512,
|
|
|
|
| 49 |
"pad_token": "[PAD]",
|
| 50 |
"sep_token": "[SEP]",
|
| 51 |
"strip_accents": null,
|
|
|
|
| 43 |
},
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
"model_max_length": 512,
|
| 50 |
+
"never_split": null,
|
| 51 |
"pad_token": "[PAD]",
|
| 52 |
"sep_token": "[SEP]",
|
| 53 |
"strip_accents": null,
|
vocab.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|