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>",
|
|
@@ -50,7 +51,6 @@
|
|
| 50 |
"rstrip": false,
|
| 51 |
"single_word": false
|
| 52 |
},
|
| 53 |
-
"special_tokens_map_file": null,
|
| 54 |
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
"unk_token": {
|
| 56 |
"__type": "AddedToken",
|
|
|
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false
|
| 10 |
},
|
| 11 |
+
"clean_up_tokenization_spaces": true,
|
| 12 |
"cls_token": {
|
| 13 |
"__type": "AddedToken",
|
| 14 |
"content": "<s>",
|
|
|
|
| 51 |
"rstrip": false,
|
| 52 |
"single_word": false
|
| 53 |
},
|
|
|
|
| 54 |
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
"unk_token": {
|
| 56 |
"__type": "AddedToken",
|