Upload tokenizer
Browse files- added_tokens.json +3 -3
- special_tokens_map.json +0 -42
- vocab.json +2 -1
added_tokens.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"</s>":
|
3 |
-
"<s>":
|
4 |
-
"[PAD]":
|
5 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 19285,
|
3 |
+
"<s>": 19284,
|
4 |
+
"[PAD]": 19286
|
5 |
}
|
special_tokens_map.json
CHANGED
@@ -1,47 +1,5 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
-
{
|
4 |
-
"content": "<s>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": true,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false
|
9 |
-
},
|
10 |
-
{
|
11 |
-
"content": "</s>",
|
12 |
-
"lstrip": false,
|
13 |
-
"normalized": true,
|
14 |
-
"rstrip": false,
|
15 |
-
"single_word": false
|
16 |
-
},
|
17 |
-
{
|
18 |
-
"content": "[PAD]",
|
19 |
-
"lstrip": false,
|
20 |
-
"normalized": true,
|
21 |
-
"rstrip": false,
|
22 |
-
"single_word": false
|
23 |
-
},
|
24 |
-
{
|
25 |
-
"content": "<s>",
|
26 |
-
"lstrip": false,
|
27 |
-
"normalized": true,
|
28 |
-
"rstrip": false,
|
29 |
-
"single_word": false
|
30 |
-
},
|
31 |
-
{
|
32 |
-
"content": "</s>",
|
33 |
-
"lstrip": false,
|
34 |
-
"normalized": true,
|
35 |
-
"rstrip": false,
|
36 |
-
"single_word": false
|
37 |
-
},
|
38 |
-
{
|
39 |
-
"content": "[PAD]",
|
40 |
-
"lstrip": false,
|
41 |
-
"normalized": true,
|
42 |
-
"rstrip": false,
|
43 |
-
"single_word": false
|
44 |
-
},
|
45 |
{
|
46 |
"content": "<s>",
|
47 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
{
|
4 |
"content": "<s>",
|
5 |
"lstrip": false,
|
vocab.json
CHANGED
@@ -19281,5 +19281,6 @@
|
|
19281 |
"zoo": 2771,
|
19282 |
"zoological": 16279,
|
19283 |
"zoology": 19082,
|
19284 |
-
"zu": 18341
|
|
|
19285 |
}
|
|
|
19281 |
"zoo": 2771,
|
19282 |
"zoological": 16279,
|
19283 |
"zoology": 19082,
|
19284 |
+
"zu": 18341,
|
19285 |
+
"|": 19283
|
19286 |
}
|