Commit
•
9d7e78c
1
Parent(s):
15416b3
Upload tokenizer
Browse files- special_tokens_map.json +0 -2
- tokenizer.json +0 -0
- tokenizer_config.json +7 -10
special_tokens_map.json
CHANGED
|
@@ -1,7 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token": "[CLS]",
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
-
"eos_token": "[SEP]",
|
| 5 |
"mask_token": "[MASK]",
|
| 6 |
"pad_token": "[PAD]",
|
| 7 |
"sep_token": "[SEP]",
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
|
|
|
| 3 |
"mask_token": "[MASK]",
|
| 4 |
"pad_token": "[PAD]",
|
| 5 |
"sep_token": "[SEP]",
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,17 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token": "[CLS]",
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
-
"do_lower_case":
|
| 5 |
-
"eos_token": "[SEP]",
|
| 6 |
"mask_token": "[MASK]",
|
| 7 |
-
"model_max_length":
|
| 8 |
-
"name_or_path": "
|
| 9 |
"pad_token": "[PAD]",
|
| 10 |
"sep_token": "[SEP]",
|
| 11 |
-
"sp_model_kwargs": {},
|
| 12 |
"special_tokens_map_file": null,
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
| 3 |
+
"do_lower_case": true,
|
|
|
|
| 4 |
"mask_token": "[MASK]",
|
| 5 |
+
"model_max_length": 512,
|
| 6 |
+
"name_or_path": "distilbert-base-uncased",
|
| 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 |
}
|