Nicola De Cao
commited on
Commit
•
b11fda7
1
Parent(s):
8a14b8b
fixing tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
tokenizer_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"model_max_length": 512, "unk_token": "[UNK]", "cls_token": "[CLS]", "sep_token": "[SEP]", "pad_token": "[PAD]", "mask_token": "[MASK]", "tokenizer_class": "PreTrainedTokenizerFast"}
|
| 1 |
+
{"model_max_length": 512, "unk_token": "[UNK]", "cls_token": "[CLS]", "sep_token": "[SEP]", "pad_token": "[PAD]", "mask_token": "[MASK]", "model_input_names": ["input_ids", "attention_mask"], "tokenizer_class": "PreTrainedTokenizerFast"}
|