Upload tokenizer
Browse files- added_tokens.json +1 -1
- special_tokens_map.json +14 -2
- tokenizer_config.json +3 -3
- vocab.json +42 -45
added_tokens.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
{
|
2 |
-
"<unk>":
|
3 |
}
|
|
|
1 |
{
|
2 |
+
"<unk>": 42
|
3 |
}
|
special_tokens_map.json
CHANGED
@@ -1,4 +1,16 @@
|
|
1 |
{
|
2 |
-
"pad_token":
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"pad_token": {
|
3 |
+
"content": "|",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"unk_token": {
|
10 |
+
"content": "<unk>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
}
|
16 |
}
|
tokenizer_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"add_blank": true,
|
3 |
"added_tokens_decoder": {
|
4 |
-
"
|
5 |
"content": "|",
|
6 |
"lstrip": false,
|
7 |
"normalized": false,
|
@@ -9,7 +9,7 @@
|
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
-
"
|
13 |
"content": "<unk>",
|
14 |
"lstrip": false,
|
15 |
"normalized": false,
|
@@ -21,7 +21,7 @@
|
|
21 |
"clean_up_tokenization_spaces": true,
|
22 |
"extra_special_tokens": {},
|
23 |
"is_uroman": false,
|
24 |
-
"language": "uzb
|
25 |
"model_max_length": 1000000000000000019884624838656,
|
26 |
"normalize": true,
|
27 |
"pad_token": "|",
|
|
|
1 |
{
|
2 |
"add_blank": true,
|
3 |
"added_tokens_decoder": {
|
4 |
+
"41": {
|
5 |
"content": "|",
|
6 |
"lstrip": false,
|
7 |
"normalized": false,
|
|
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
+
"42": {
|
13 |
"content": "<unk>",
|
14 |
"lstrip": false,
|
15 |
"normalized": false,
|
|
|
21 |
"clean_up_tokenization_spaces": true,
|
22 |
"extra_special_tokens": {},
|
23 |
"is_uroman": false,
|
24 |
+
"language": "uzb",
|
25 |
"model_max_length": 1000000000000000019884624838656,
|
26 |
"normalize": true,
|
27 |
"pad_token": "|",
|
vocab.json
CHANGED
@@ -1,47 +1,44 @@
|
|
1 |
{
|
2 |
-
" ":
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
44 |
-
"ҳ": 21,
|
45 |
-
"–": 32,
|
46 |
-
"—": 33
|
47 |
}
|
|
|
1 |
{
|
2 |
+
" ": 0,
|
3 |
+
"!": 1,
|
4 |
+
"'": 2,
|
5 |
+
"(": 3,
|
6 |
+
")": 4,
|
7 |
+
",": 5,
|
8 |
+
"-": 6,
|
9 |
+
".": 7,
|
10 |
+
":": 8,
|
11 |
+
";": 9,
|
12 |
+
"?": 10,
|
13 |
+
"a": 11,
|
14 |
+
"b": 12,
|
15 |
+
"c": 13,
|
16 |
+
"d": 14,
|
17 |
+
"e": 15,
|
18 |
+
"f": 16,
|
19 |
+
"g": 17,
|
20 |
+
"h": 18,
|
21 |
+
"i": 19,
|
22 |
+
"j": 20,
|
23 |
+
"k": 21,
|
24 |
+
"l": 22,
|
25 |
+
"m": 23,
|
26 |
+
"n": 24,
|
27 |
+
"o": 25,
|
28 |
+
"p": 26,
|
29 |
+
"q": 27,
|
30 |
+
"r": 28,
|
31 |
+
"s": 29,
|
32 |
+
"t": 30,
|
33 |
+
"u": 31,
|
34 |
+
"v": 32,
|
35 |
+
"w": 33,
|
36 |
+
"x": 34,
|
37 |
+
"y": 35,
|
38 |
+
"z": 36,
|
39 |
+
"|": 41,
|
40 |
+
"ç": 37,
|
41 |
+
"ğ": 38,
|
42 |
+
"ō": 39,
|
43 |
+
"ş": 40
|
|
|
|
|
|
|
44 |
}
|