Updates incorrect tokenizer configuration file
#1
by
lysandre
HF staff
- opened
- tokenizer_config.json +1 -16
tokenizer_config.json
CHANGED
|
@@ -1,16 +1 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_lower_case": true,
|
| 3 |
-
"do_basic_tokenize": true,
|
| 4 |
-
"never_split": null,
|
| 5 |
-
"unk_token": "[UNK]",
|
| 6 |
-
"sep_token": "[SEP]",
|
| 7 |
-
"pad_token": "[PAD]",
|
| 8 |
-
"cls_token": "[CLS]",
|
| 9 |
-
"mask_token": "[MASK]",
|
| 10 |
-
"tokenize_chinese_chars": true,
|
| 11 |
-
"strip_accents": null,
|
| 12 |
-
"special_tokens_map_file": null,
|
| 13 |
-
"tokenizer_file": null,
|
| 14 |
-
"name_or_path": "junnyu/roformer_chinese_char_base",
|
| 15 |
-
"tokenizer_class": "BertTokenizer"
|
| 16 |
-
}
|
|
|
|
| 1 |
+
{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "junnyu/roformer_chinese_char_base", "tokenizer_class": "BertTokenizer", "model_max_length": 512}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|