kimsan0622
commited on
Commit
•
a4c3e1b
1
Parent(s):
63d9dca
Upload tokenizer
Browse files- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "!",
|
3 |
+
"cls_token": "&",
|
4 |
+
"eos_token": "\"",
|
5 |
+
"mask_token": "'",
|
6 |
+
"pad_token": "%",
|
7 |
+
"sep_token": "$",
|
8 |
+
"unk_token": "#"
|
9 |
+
}
|
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 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"model_max_length": 1000000000000000019884624838656,
|
4 |
+
"special_tokens": [
|
5 |
+
"<s>",
|
6 |
+
"</s>",
|
7 |
+
"<unk>",
|
8 |
+
"<sep>",
|
9 |
+
"<pad>",
|
10 |
+
"<cls>",
|
11 |
+
"<mask>"
|
12 |
+
],
|
13 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
14 |
+
}
|