wannaphong
commited on
Commit
•
b05b65a
1
Parent(s):
fbe7929
Upload tokenizer
Browse files- .gitattributes +1 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +17 -0
- tokenizer.json +3 -0
- tokenizer_config.json +21 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c49dc7e82c10227af764e518924cf2f9d50c00462750d184fa74697bba65eef8
|
3 |
+
size 4920706
|
special_tokens_map.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<madeupword0>",
|
4 |
+
"<madeupword1>",
|
5 |
+
"<madeupword2>",
|
6 |
+
"<madeupword3>",
|
7 |
+
"<madeupword4>",
|
8 |
+
"<madeupword5>",
|
9 |
+
"<madeupword6>"
|
10 |
+
],
|
11 |
+
"bos_token": "<s>",
|
12 |
+
"cls_token": "<s>",
|
13 |
+
"eos_token": "</s>",
|
14 |
+
"pad_token": "<pad>",
|
15 |
+
"sep_token": "</s>",
|
16 |
+
"unk_token": "<unk>"
|
17 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00d163342a36b3ad1ea2f5f608e6bb2b2ff29bd453a41c4f52525a7ebc7c4b6a
|
3 |
+
size 17210041
|
tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<madeupword0>",
|
4 |
+
"<madeupword1>",
|
5 |
+
"<madeupword2>",
|
6 |
+
"<madeupword3>",
|
7 |
+
"<madeupword4>",
|
8 |
+
"<madeupword5>",
|
9 |
+
"<madeupword6>"
|
10 |
+
],
|
11 |
+
"bos_token": "<s>",
|
12 |
+
"clean_up_tokenization_spaces": true,
|
13 |
+
"cls_token": "<s>",
|
14 |
+
"eos_token": "</s>",
|
15 |
+
"model_max_length": 1000000000000000019884624838656,
|
16 |
+
"pad_token": "<pad>",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"sp_model_kwargs": {},
|
19 |
+
"tokenizer_class": "XGLMTokenizer",
|
20 |
+
"unk_token": "<unk>"
|
21 |
+
}
|