Commit
•
aabaeb0
1
Parent(s):
e1d2014
Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +7 -2
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,11 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
| 3 |
"mask_token": "[MASK]",
|
| 4 |
"pad_token": "[PAD]",
|
|
|
|
| 1 |
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"[PAD]",
|
| 4 |
+
"[UNK]",
|
| 5 |
+
"[CLS]",
|
| 6 |
+
"[SEP]",
|
| 7 |
+
"[MASK]"
|
| 8 |
+
],
|
| 9 |
"cls_token": "[CLS]",
|
| 10 |
"mask_token": "[MASK]",
|
| 11 |
"pad_token": "[PAD]",
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -41,7 +41,13 @@
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
-
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
"clean_up_tokenization_spaces": true,
|
| 46 |
"cls_token": "[CLS]",
|
| 47 |
"do_basic_tokenize": true,
|
|
@@ -54,6 +60,5 @@
|
|
| 54 |
"strip_accents": null,
|
| 55 |
"tokenize_chinese_chars": true,
|
| 56 |
"tokenizer_class": "BertTokenizer",
|
| 57 |
-
"tokenizer_file": null,
|
| 58 |
"unk_token": "[UNK]"
|
| 59 |
}
|
|
|
|
| 41 |
"special": true
|
| 42 |
}
|
| 43 |
},
|
| 44 |
+
"additional_special_tokens": [
|
| 45 |
+
"[PAD]",
|
| 46 |
+
"[UNK]",
|
| 47 |
+
"[CLS]",
|
| 48 |
+
"[SEP]",
|
| 49 |
+
"[MASK]"
|
| 50 |
+
],
|
| 51 |
"clean_up_tokenization_spaces": true,
|
| 52 |
"cls_token": "[CLS]",
|
| 53 |
"do_basic_tokenize": true,
|
|
|
|
| 60 |
"strip_accents": null,
|
| 61 |
"tokenize_chinese_chars": true,
|
| 62 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
| 63 |
"unk_token": "[UNK]"
|
| 64 |
}
|