Upload processor
Browse files- tokenizer_config.json +4 -4
- vocab.json +5 -8
tokenizer_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
-
"
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": true,
|
6 |
"normalized": false,
|
@@ -8,7 +8,7 @@
|
|
8 |
"single_word": false,
|
9 |
"special": false
|
10 |
},
|
11 |
-
"
|
12 |
"content": "[PAD]",
|
13 |
"lstrip": true,
|
14 |
"normalized": false,
|
@@ -16,7 +16,7 @@
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
-
"
|
20 |
"content": "<s>",
|
21 |
"lstrip": true,
|
22 |
"normalized": false,
|
@@ -24,7 +24,7 @@
|
|
24 |
"single_word": false,
|
25 |
"special": false
|
26 |
},
|
27 |
-
"
|
28 |
"content": "</s>",
|
29 |
"lstrip": true,
|
30 |
"normalized": false,
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
+
"28": {
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": true,
|
6 |
"normalized": false,
|
|
|
8 |
"single_word": false,
|
9 |
"special": false
|
10 |
},
|
11 |
+
"29": {
|
12 |
"content": "[PAD]",
|
13 |
"lstrip": true,
|
14 |
"normalized": false,
|
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
+
"30": {
|
20 |
"content": "<s>",
|
21 |
"lstrip": true,
|
22 |
"normalized": false,
|
|
|
24 |
"single_word": false,
|
25 |
"special": false
|
26 |
},
|
27 |
+
"31": {
|
28 |
"content": "</s>",
|
29 |
"lstrip": true,
|
30 |
"normalized": false,
|
vocab.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"'": 1,
|
3 |
-
"</s>":
|
4 |
-
"<s>":
|
5 |
-
"[PAD]":
|
6 |
-
"[UNK]":
|
7 |
"a": 2,
|
8 |
"b": 3,
|
9 |
"c": 4,
|
@@ -30,8 +30,5 @@
|
|
30 |
"x": 25,
|
31 |
"y": 26,
|
32 |
"z": 27,
|
33 |
-
"|": 0
|
34 |
-
"ù": 28,
|
35 |
-
"ả": 29,
|
36 |
-
"ệ": 30
|
37 |
}
|
|
|
1 |
{
|
2 |
"'": 1,
|
3 |
+
"</s>": 31,
|
4 |
+
"<s>": 30,
|
5 |
+
"[PAD]": 29,
|
6 |
+
"[UNK]": 28,
|
7 |
"a": 2,
|
8 |
"b": 3,
|
9 |
"c": 4,
|
|
|
30 |
"x": 25,
|
31 |
"y": 26,
|
32 |
"z": 27,
|
33 |
+
"|": 0
|
|
|
|
|
|
|
34 |
}
|