Fix tokenizer files
Browse files- preprocessor_config.json +2 -1
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
preprocessor_config.json
CHANGED
@@ -13,5 +13,6 @@
|
|
13 |
0.5
|
14 |
],
|
15 |
"resample": 3,
|
16 |
-
"size": 384
|
|
|
17 |
}
|
|
|
13 |
0.5
|
14 |
],
|
15 |
"resample": 3,
|
16 |
+
"size": 384,
|
17 |
+
"size_divisor": 32
|
18 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"do_lower_case": true, "
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
|