Upload tokenizer
Browse files- added_tokens.json +2 -2
- tokenizer_config.json +6 -6
- vocab.json +10 -9
added_tokens.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"</s>":
|
3 |
-
"<s>":
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 43,
|
3 |
+
"<s>": 42
|
4 |
}
|
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,
|
@@ -16,18 +16,18 @@
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
-
"
|
20 |
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
-
"normalized":
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
-
"normalized":
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
+
"40": {
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": true,
|
6 |
"normalized": false,
|
|
|
8 |
"single_word": false,
|
9 |
"special": false
|
10 |
},
|
11 |
+
"41": {
|
12 |
"content": "[PAD]",
|
13 |
"lstrip": true,
|
14 |
"normalized": false,
|
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
+
"42": {
|
20 |
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"43": {
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
vocab.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"(": 1,
|
3 |
")": 2,
|
4 |
-
"[PAD]":
|
5 |
-
"[UNK]":
|
6 |
"a": 3,
|
7 |
"b": 4,
|
8 |
"c": 5,
|
@@ -33,11 +33,12 @@
|
|
33 |
"ç": 29,
|
34 |
"é": 30,
|
35 |
"ë": 31,
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
|
|
43 |
}
|
|
|
1 |
{
|
2 |
"(": 1,
|
3 |
")": 2,
|
4 |
+
"[PAD]": 41,
|
5 |
+
"[UNK]": 40,
|
6 |
"a": 3,
|
7 |
"b": 4,
|
8 |
"c": 5,
|
|
|
33 |
"ç": 29,
|
34 |
"é": 30,
|
35 |
"ë": 31,
|
36 |
+
"ö": 32,
|
37 |
+
"ü": 33,
|
38 |
+
"ğ": 34,
|
39 |
+
"ı": 35,
|
40 |
+
"ş": 36,
|
41 |
+
"̇": 37,
|
42 |
+
"’": 38,
|
43 |
+
"…": 39
|
44 |
}
|