Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +2 -1
- vocab.json +0 -0
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -48,9 +48,10 @@
|
|
| 48 |
"eos_token": "</s>",
|
| 49 |
"errors": "replace",
|
| 50 |
"mask_token": "<mask>",
|
| 51 |
-
"model_max_length":
|
| 52 |
"pad_token": "<pad>",
|
| 53 |
"sep_token": "</s>",
|
| 54 |
"tokenizer_class": "BartTokenizer",
|
|
|
|
| 55 |
"unk_token": "<unk>"
|
| 56 |
}
|
|
|
|
| 48 |
"eos_token": "</s>",
|
| 49 |
"errors": "replace",
|
| 50 |
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
"pad_token": "<pad>",
|
| 53 |
"sep_token": "</s>",
|
| 54 |
"tokenizer_class": "BartTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
"unk_token": "<unk>"
|
| 57 |
}
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|