fix: tokenizer
Browse files- tokenizer_config.json +15 -1
- vocab.txt +0 -0
tokenizer_config.json
CHANGED
|
@@ -1 +1,15 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_lower_case": false,
|
| 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 |
+
"max_model_length": 512,
|
| 13 |
+
"special_tokens_map_file": null,
|
| 14 |
+
"tokenizer_file": null
|
| 15 |
+
}
|
vocab.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|