add tokenizer
Browse files- merges.txt +0 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
merges.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -53,6 +53,7 @@
|
|
| 53 |
},
|
| 54 |
"special_tokens_map_file": null,
|
| 55 |
"tokenizer_class": "RobertaTokenizer",
|
|
|
|
| 56 |
"unk_token": {
|
| 57 |
"__type": "AddedToken",
|
| 58 |
"content": "<unk>",
|
|
|
|
| 53 |
},
|
| 54 |
"special_tokens_map_file": null,
|
| 55 |
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
"unk_token": {
|
| 58 |
"__type": "AddedToken",
|
| 59 |
"content": "<unk>",
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|