updated tokenizer on 2024-04-14, 14:36:44
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +2 -0
- vocab.json +0 -0
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -51,7 +51,9 @@
|
|
| 51 |
"max_len": 512,
|
| 52 |
"model_max_length": 512,
|
| 53 |
"pad_token": "<pad>",
|
|
|
|
| 54 |
"sep_token": "</s>",
|
| 55 |
"tokenizer_class": "RobertaTokenizer",
|
|
|
|
| 56 |
"unk_token": "<unk>"
|
| 57 |
}
|
|
|
|
| 51 |
"max_len": 512,
|
| 52 |
"model_max_length": 512,
|
| 53 |
"pad_token": "<pad>",
|
| 54 |
+
"return_attention_mask": true,
|
| 55 |
"sep_token": "</s>",
|
| 56 |
"tokenizer_class": "RobertaTokenizer",
|
| 57 |
+
"trim_offsets": true,
|
| 58 |
"unk_token": "<unk>"
|
| 59 |
}
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|