Mojtaba aka Omid Rohanian
commited on
Commit
·
2cfaf74
1
Parent(s):
d3dd429
fixed the tokeniser
Browse files- tokenizer_config.json +2 -2
tokenizer_config.json
CHANGED
@@ -3,12 +3,12 @@
|
|
3 |
"do_lower_case": false,
|
4 |
"mask_token": "[MASK]",
|
5 |
"model_max_length": 512,
|
6 |
-
"name_or_path": "
|
7 |
"pad_token": "[PAD]",
|
8 |
"sep_token": "[SEP]",
|
9 |
"special_tokens_map_file": null,
|
10 |
"strip_accents": null,
|
11 |
"tokenize_chinese_chars": true,
|
12 |
-
"tokenizer_class": "
|
13 |
"unk_token": "[UNK]"
|
14 |
}
|
|
|
3 |
"do_lower_case": false,
|
4 |
"mask_token": "[MASK]",
|
5 |
"model_max_length": 512,
|
6 |
+
"name_or_path": "distilbert-base-cased",
|
7 |
"pad_token": "[PAD]",
|
8 |
"sep_token": "[SEP]",
|
9 |
"special_tokens_map_file": null,
|
10 |
"strip_accents": null,
|
11 |
"tokenize_chinese_chars": true,
|
12 |
+
"tokenizer_class": "DistilBertTokenizer",
|
13 |
"unk_token": "[UNK]"
|
14 |
}
|