Upload tokenizer
Browse files- special_tokens_map.json +2 -4
- tokenizer.json +0 -0
- tokenizer_config.json +9 -16
- vocab.txt +0 -0
special_tokens_map.json
CHANGED
|
@@ -1,9 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token": "[CLS]",
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
-
"eos_token": "[SEP]",
|
| 5 |
"mask_token": "[MASK]",
|
| 6 |
-
"pad_token": "
|
| 7 |
"sep_token": "[SEP]",
|
| 8 |
-
"unk_token": "
|
| 9 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
|
|
|
| 3 |
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,23 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token": "[CLS]",
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"mask_token": {
|
| 8 |
-
"__type": "AddedToken",
|
| 9 |
-
"content": "[MASK]",
|
| 10 |
-
"lstrip": true,
|
| 11 |
-
"normalized": true,
|
| 12 |
-
"rstrip": false,
|
| 13 |
-
"single_word": false
|
| 14 |
-
},
|
| 15 |
"model_max_length": 512,
|
| 16 |
"name_or_path": "ft-models",
|
| 17 |
-
"
|
| 18 |
-
"
|
| 19 |
"sep_token": "[SEP]",
|
| 20 |
"special_tokens_map_file": null,
|
| 21 |
-
"
|
| 22 |
-
"
|
|
|
|
|
|
|
| 23 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
| 3 |
+
"do_basic_tokenize": true,
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"mask_token": "[MASK]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"model_max_length": 512,
|
| 7 |
"name_or_path": "ft-models",
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
"sep_token": "[SEP]",
|
| 11 |
"special_tokens_map_file": null,
|
| 12 |
+
"strip_accents": null,
|
| 13 |
+
"tokenize_chinese_chars": true,
|
| 14 |
+
"tokenizer_class": "BertTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|