Upload tokenizer.json
Browse filesUpdated tokenizer.json
- tokenizer.json +12 -11
tokenizer.json
CHANGED
@@ -5,48 +5,48 @@
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
|
|
8 |
"content": "<s>",
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
12 |
-
"normalized": false
|
13 |
-
"special": true
|
14 |
},
|
15 |
{
|
16 |
"id": 1,
|
|
|
17 |
"content": "<pad>",
|
18 |
"single_word": false,
|
19 |
"lstrip": false,
|
20 |
"rstrip": false,
|
21 |
-
"normalized": false
|
22 |
-
"special": true
|
23 |
},
|
24 |
{
|
25 |
"id": 2,
|
|
|
26 |
"content": "</s>",
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
29 |
"rstrip": false,
|
30 |
-
"normalized": false
|
31 |
-
"special": true
|
32 |
},
|
33 |
{
|
34 |
"id": 3,
|
|
|
35 |
"content": "<unk>",
|
36 |
"single_word": false,
|
37 |
"lstrip": false,
|
38 |
"rstrip": false,
|
39 |
-
"normalized": false
|
40 |
-
"special": true
|
41 |
},
|
42 |
{
|
43 |
"id": 128000,
|
|
|
44 |
"content": "<mask>",
|
45 |
"single_word": false,
|
46 |
"lstrip": true,
|
47 |
"rstrip": false,
|
48 |
-
"normalized": false
|
49 |
-
"special": true
|
50 |
}
|
51 |
],
|
52 |
"normalizer": {
|
@@ -55,7 +55,8 @@
|
|
55 |
"pre_tokenizer": {
|
56 |
"type": "Metaspace",
|
57 |
"replacement": "▁",
|
58 |
-
"add_prefix_space":
|
|
|
59 |
},
|
60 |
"post_processor": {
|
61 |
"type": "RobertaProcessing",
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
8 |
+
"special": true,
|
9 |
"content": "<s>",
|
10 |
"single_word": false,
|
11 |
"lstrip": false,
|
12 |
"rstrip": false,
|
13 |
+
"normalized": false
|
|
|
14 |
},
|
15 |
{
|
16 |
"id": 1,
|
17 |
+
"special": true,
|
18 |
"content": "<pad>",
|
19 |
"single_word": false,
|
20 |
"lstrip": false,
|
21 |
"rstrip": false,
|
22 |
+
"normalized": false
|
|
|
23 |
},
|
24 |
{
|
25 |
"id": 2,
|
26 |
+
"special": true,
|
27 |
"content": "</s>",
|
28 |
"single_word": false,
|
29 |
"lstrip": false,
|
30 |
"rstrip": false,
|
31 |
+
"normalized": false
|
|
|
32 |
},
|
33 |
{
|
34 |
"id": 3,
|
35 |
+
"special": true,
|
36 |
"content": "<unk>",
|
37 |
"single_word": false,
|
38 |
"lstrip": false,
|
39 |
"rstrip": false,
|
40 |
+
"normalized": false
|
|
|
41 |
},
|
42 |
{
|
43 |
"id": 128000,
|
44 |
+
"special": true,
|
45 |
"content": "<mask>",
|
46 |
"single_word": false,
|
47 |
"lstrip": true,
|
48 |
"rstrip": false,
|
49 |
+
"normalized": false
|
|
|
50 |
}
|
51 |
],
|
52 |
"normalizer": {
|
|
|
55 |
"pre_tokenizer": {
|
56 |
"type": "Metaspace",
|
57 |
"replacement": "▁",
|
58 |
+
"add_prefix_space": true,
|
59 |
+
"prepend_scheme": "never"
|
60 |
},
|
61 |
"post_processor": {
|
62 |
"type": "RobertaProcessing",
|