Upload tokenizer
Browse files- merges.txt +0 -0
- tokenizer.json +0 -0
- tokenizer_config.json +2 -1
- vocab.json +0 -0
merges.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -35,7 +35,7 @@
|
|
| 35 |
"single_word": false
|
| 36 |
},
|
| 37 |
"model_max_length": 512,
|
| 38 |
-
"name_or_path": "
|
| 39 |
"pad_token": {
|
| 40 |
"__type": "AddedToken",
|
| 41 |
"content": "<pad>",
|
|
@@ -54,6 +54,7 @@
|
|
| 54 |
},
|
| 55 |
"special_tokens_map_file": null,
|
| 56 |
"tokenizer_class": "RobertaTokenizer",
|
|
|
|
| 57 |
"unk_token": {
|
| 58 |
"__type": "AddedToken",
|
| 59 |
"content": "<unk>",
|
|
|
|
| 35 |
"single_word": false
|
| 36 |
},
|
| 37 |
"model_max_length": 512,
|
| 38 |
+
"name_or_path": "SuiGio/roberta_pubmesh",
|
| 39 |
"pad_token": {
|
| 40 |
"__type": "AddedToken",
|
| 41 |
"content": "<pad>",
|
|
|
|
| 54 |
},
|
| 55 |
"special_tokens_map_file": null,
|
| 56 |
"tokenizer_class": "RobertaTokenizer",
|
| 57 |
+
"trim_offsets": true,
|
| 58 |
"unk_token": {
|
| 59 |
"__type": "AddedToken",
|
| 60 |
"content": "<unk>",
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|