Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +5 -7
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,16 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"backend": "tokenizers",
|
| 3 |
-
"clean_up_tokenization_spaces": true,
|
| 4 |
"cls_token": "[CLS]",
|
|
|
|
| 5 |
"is_local": false,
|
| 6 |
"mask_token": "[MASK]",
|
| 7 |
-
"
|
| 8 |
-
"input_ids",
|
| 9 |
-
"attention_mask"
|
| 10 |
-
],
|
| 11 |
-
"model_max_length": 8192,
|
| 12 |
"pad_token": "[PAD]",
|
| 13 |
"sep_token": "[SEP]",
|
| 14 |
-
"
|
|
|
|
|
|
|
| 15 |
"unk_token": "[UNK]"
|
| 16 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"backend": "tokenizers",
|
|
|
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
"is_local": false,
|
| 6 |
"mask_token": "[MASK]",
|
| 7 |
+
"model_max_length": 512,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"pad_token": "[PAD]",
|
| 9 |
"sep_token": "[SEP]",
|
| 10 |
+
"strip_accents": null,
|
| 11 |
+
"tokenize_chinese_chars": true,
|
| 12 |
+
"tokenizer_class": "BertTokenizer",
|
| 13 |
"unk_token": "[UNK]"
|
| 14 |
}
|