delete tokenizer folder (#3)
Browse files- delete tokenizer folder (028c3478c4b1e9231ecf4b68594555856f1cb88b)
Co-authored-by: Joe Berria <[email protected]>
- tokenizer/special_tokens_map.json +0 -7
- tokenizer/tokenizer_config.json +0 -15
- tokenizer/vocab.txt +0 -0
tokenizer/special_tokens_map.json
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"cls_token": "[CLS]",
|
| 3 |
-
"mask_token": "[MASK]",
|
| 4 |
-
"pad_token": "[PAD]",
|
| 5 |
-
"sep_token": "[SEP]",
|
| 6 |
-
"unk_token": "[UNK]"
|
| 7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer/tokenizer_config.json
DELETED
|
@@ -1,15 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"clean_up_tokenization_spaces": true,
|
| 3 |
-
"cls_token": "[CLS]",
|
| 4 |
-
"do_basic_tokenize": true,
|
| 5 |
-
"do_lower_case": true,
|
| 6 |
-
"mask_token": "[MASK]",
|
| 7 |
-
"model_max_length": 512,
|
| 8 |
-
"never_split": null,
|
| 9 |
-
"pad_token": "[PAD]",
|
| 10 |
-
"sep_token": "[SEP]",
|
| 11 |
-
"strip_accents": null,
|
| 12 |
-
"tokenize_chinese_chars": true,
|
| 13 |
-
"tokenizer_class": "DistilBertTokenizer",
|
| 14 |
-
"unk_token": "[UNK]"
|
| 15 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer/vocab.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|