phamvanlinh143
commited on
Commit
•
48be254
1
Parent(s):
3f3da2d
add tokenizer
Browse files- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +19 -0
- tokenizer.json +0 -0
- tokenizer_config.json +24 -0
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
|
3 |
+
size 810912
|
special_tokens_map.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"cls_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"mask_token": {
|
10 |
+
"content": "<mask>",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<pad>",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"unk_token": "<unk>"
|
19 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"cls_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"mask_token": {
|
10 |
+
"__type": "AddedToken",
|
11 |
+
"content": "<mask>",
|
12 |
+
"lstrip": true,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
"model_max_length": 512,
|
18 |
+
"name_or_path": "camembert-base",
|
19 |
+
"pad_token": "<pad>",
|
20 |
+
"sep_token": "</s>",
|
21 |
+
"special_tokens_map_file": null,
|
22 |
+
"tokenizer_class": "CamembertTokenizer",
|
23 |
+
"unk_token": "<unk>"
|
24 |
+
}
|