Upload tokenizer
Browse files- tokenizer_config.json +7 -0
tokenizer_config.json
CHANGED
|
@@ -45,11 +45,18 @@
|
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_lower_case": true,
|
| 47 |
"mask_token": "[MASK]",
|
|
|
|
| 48 |
"model_max_length": 512,
|
|
|
|
| 49 |
"pad_token": "[PAD]",
|
|
|
|
|
|
|
| 50 |
"sep_token": "[SEP]",
|
|
|
|
| 51 |
"strip_accents": null,
|
| 52 |
"tokenize_chinese_chars": true,
|
| 53 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
|
|
|
| 54 |
"unk_token": "[UNK]"
|
| 55 |
}
|
|
|
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"do_lower_case": true,
|
| 47 |
"mask_token": "[MASK]",
|
| 48 |
+
"max_length": 512,
|
| 49 |
"model_max_length": 512,
|
| 50 |
+
"pad_to_multiple_of": null,
|
| 51 |
"pad_token": "[PAD]",
|
| 52 |
+
"pad_token_type_id": 0,
|
| 53 |
+
"padding_side": "right",
|
| 54 |
"sep_token": "[SEP]",
|
| 55 |
+
"stride": 0,
|
| 56 |
"strip_accents": null,
|
| 57 |
"tokenize_chinese_chars": true,
|
| 58 |
"tokenizer_class": "BertTokenizer",
|
| 59 |
+
"truncation_side": "right",
|
| 60 |
+
"truncation_strategy": "longest_first",
|
| 61 |
"unk_token": "[UNK]"
|
| 62 |
}
|