Erica tong
commited on
Commit
•
288effa
1
Parent(s):
2c86e42
Upload tokenizer
Browse files- tokenizer_config.json +3 -1
tokenizer_config.json
CHANGED
@@ -1,15 +1,17 @@
|
|
1 |
{
|
2 |
"cls_token": "[CLS]",
|
|
|
3 |
"do_lower_case": true,
|
4 |
"mask_token": "[MASK]",
|
5 |
"model_max_length": 512,
|
6 |
"name_or_path": "HFFErica/my_model_Eperiment2",
|
|
|
7 |
"pad_token": "[PAD]",
|
8 |
"padding_side": "left",
|
9 |
"sep_token": "[SEP]",
|
10 |
"special_tokens_map_file": null,
|
11 |
"strip_accents": null,
|
12 |
"tokenize_chinese_chars": true,
|
13 |
-
"tokenizer_class": "
|
14 |
"unk_token": "[UNK]"
|
15 |
}
|
|
|
1 |
{
|
2 |
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
"do_lower_case": true,
|
5 |
"mask_token": "[MASK]",
|
6 |
"model_max_length": 512,
|
7 |
"name_or_path": "HFFErica/my_model_Eperiment2",
|
8 |
+
"never_split": null,
|
9 |
"pad_token": "[PAD]",
|
10 |
"padding_side": "left",
|
11 |
"sep_token": "[SEP]",
|
12 |
"special_tokens_map_file": null,
|
13 |
"strip_accents": null,
|
14 |
"tokenize_chinese_chars": true,
|
15 |
+
"tokenizer_class": "BertTokenizer",
|
16 |
"unk_token": "[UNK]"
|
17 |
}
|