Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +6 -15
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,23 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space": true,
|
| 3 |
"backend": "tokenizers",
|
| 4 |
-
"bos_token": "[CLS]",
|
| 5 |
"cls_token": "[CLS]",
|
| 6 |
-
"do_lower_case":
|
| 7 |
-
"eos_token": "[SEP]",
|
| 8 |
-
"extra_special_tokens": [
|
| 9 |
-
"[PAD]",
|
| 10 |
-
"[CLS]",
|
| 11 |
-
"[SEP]"
|
| 12 |
-
],
|
| 13 |
"is_local": false,
|
| 14 |
"mask_token": "[MASK]",
|
| 15 |
-
"model_max_length":
|
| 16 |
"pad_token": "[PAD]",
|
| 17 |
"sep_token": "[SEP]",
|
| 18 |
-
"
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
-
"unk_token": "[UNK]"
|
| 22 |
-
"vocab_type": "spm"
|
| 23 |
}
|
|
|
|
| 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 |
}
|