Kaspar Beelen
commited on
Commit
•
e955632
1
Parent(s):
b240b50
add tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +10 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[DATE]": 30522
|
3 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"[DATE]"
|
4 |
+
],
|
5 |
+
"cls_token": "[CLS]",
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"unk_token": "[UNK]"
|
10 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": true,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"model_max_length": 512,
|
6 |
+
"name_or_path": "erwt-year-masked-25",
|
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 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|