Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +4 -2
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -43,15 +43,17 @@
|
|
| 43 |
},
|
| 44 |
"clean_up_tokenization_spaces": false,
|
| 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,
|
| 54 |
"tokenize_chinese_chars": true,
|
| 55 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
|
|
|
| 56 |
"unk_token": "[UNK]"
|
| 57 |
}
|
|
|
|
| 43 |
},
|
| 44 |
"clean_up_tokenization_spaces": false,
|
| 45 |
"cls_token": "[CLS]",
|
|
|
|
| 46 |
"do_lower_case": true,
|
| 47 |
"mask_token": "[MASK]",
|
| 48 |
+
"max_length": 10,
|
| 49 |
"model_max_length": 512,
|
|
|
|
| 50 |
"pad_token": "[PAD]",
|
| 51 |
"sep_token": "[SEP]",
|
| 52 |
+
"stride": 0,
|
| 53 |
"strip_accents": null,
|
| 54 |
"tokenize_chinese_chars": true,
|
| 55 |
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"truncation_side": "right",
|
| 57 |
+
"truncation_strategy": "longest_first",
|
| 58 |
"unk_token": "[UNK]"
|
| 59 |
}
|