xaviergillard
commited on
Commit
•
3abd111
1
Parent(s):
1d4443a
Upload tokenizer
Browse files- added_tokens.json +5 -5
- tokenizer_config.json +5 -5
- vocab.txt +0 -0
added_tokens.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"[CLS]":
|
3 |
-
"[MASK]":
|
4 |
-
"[PAD]":
|
5 |
-
"[SEP]":
|
6 |
-
"[UNK]":
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"[CLS]": 24312,
|
3 |
+
"[MASK]": 24313,
|
4 |
+
"[PAD]": 24311,
|
5 |
+
"[SEP]": 24310,
|
6 |
+
"[UNK]": 24309
|
7 |
}
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
-
"
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
@@ -8,7 +8,7 @@
|
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
"content": "[SEP]",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
@@ -16,7 +16,7 @@
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
"content": "[PAD]",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
@@ -24,7 +24,7 @@
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
"content": "[CLS]",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
@@ -32,7 +32,7 @@
|
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
"content": "[MASK]",
|
37 |
"lstrip": false,
|
38 |
"normalized": false,
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
+
"24309": {
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
|
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"24310": {
|
12 |
"content": "[SEP]",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"24311": {
|
20 |
"content": "[PAD]",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"24312": {
|
28 |
"content": "[CLS]",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
|
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
+
"24313": {
|
36 |
"content": "[MASK]",
|
37 |
"lstrip": false,
|
38 |
"normalized": false,
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|