Upload tokenizer
Browse files- tokenizer_config.json +2 -0
tokenizer_config.json
CHANGED
|
@@ -43,11 +43,13 @@
|
|
| 43 |
},
|
| 44 |
"clean_up_tokenization_spaces": false,
|
| 45 |
"cls_token": "[CLS]",
|
|
|
|
| 46 |
"do_lower_case": true,
|
| 47 |
"extra_special_tokens": {},
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
"max_length": 128,
|
| 50 |
"model_max_length": 512,
|
|
|
|
| 51 |
"pad_to_multiple_of": null,
|
| 52 |
"pad_token": "[PAD]",
|
| 53 |
"pad_token_type_id": 0,
|
|
|
|
| 43 |
},
|
| 44 |
"clean_up_tokenization_spaces": false,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
"do_lower_case": true,
|
| 48 |
"extra_special_tokens": {},
|
| 49 |
"mask_token": "[MASK]",
|
| 50 |
"max_length": 128,
|
| 51 |
"model_max_length": 512,
|
| 52 |
+
"never_split": null,
|
| 53 |
"pad_to_multiple_of": null,
|
| 54 |
"pad_token": "[PAD]",
|
| 55 |
"pad_token_type_id": 0,
|