Update tokenizer_config.json
#12
by
freaksamael
- opened
- tokenizer_config.json +2 -2
tokenizer_config.json
CHANGED
@@ -4,12 +4,12 @@
|
|
4 |
"do_basic_tokenize": true,
|
5 |
"do_lower_case": true,
|
6 |
"mask_token": "[MASK]",
|
7 |
-
"model_max_length":
|
8 |
"never_split": null,
|
9 |
"pad_token": "[PAD]",
|
10 |
"sep_token": "[SEP]",
|
11 |
"strip_accents": null,
|
12 |
-
"tokenize_chinese_chars":
|
13 |
"tokenizer_class": "BertTokenizer",
|
14 |
"unk_token": "[UNK]"
|
15 |
}
|
|
|
4 |
"do_basic_tokenize": true,
|
5 |
"do_lower_case": true,
|
6 |
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 2048,
|
8 |
"never_split": null,
|
9 |
"pad_token": "[PAD]",
|
10 |
"sep_token": "[SEP]",
|
11 |
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": false,
|
13 |
"tokenizer_class": "BertTokenizer",
|
14 |
"unk_token": "[UNK]"
|
15 |
}
|