Commit
路
d7881a4
1
Parent(s):
659f8e8
Upload tokenizer
Browse files- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
@@ -8,6 +8,7 @@
|
|
8 |
"rstrip": false,
|
9 |
"single_word": false
|
10 |
},
|
|
|
11 |
"cls_token": {
|
12 |
"__type": "AddedToken",
|
13 |
"content": "<s>",
|
@@ -51,7 +52,6 @@
|
|
51 |
"rstrip": false,
|
52 |
"single_word": false
|
53 |
},
|
54 |
-
"special_tokens_map_file": null,
|
55 |
"tokenizer_class": "RobertaTokenizer",
|
56 |
"trim_offsets": true,
|
57 |
"unk_token": {
|
|
|
8 |
"rstrip": false,
|
9 |
"single_word": false
|
10 |
},
|
11 |
+
"clean_up_tokenization_spaces": true,
|
12 |
"cls_token": {
|
13 |
"__type": "AddedToken",
|
14 |
"content": "<s>",
|
|
|
52 |
"rstrip": false,
|
53 |
"single_word": false
|
54 |
},
|
|
|
55 |
"tokenizer_class": "RobertaTokenizer",
|
56 |
"trim_offsets": true,
|
57 |
"unk_token": {
|