Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +7 -0
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -48,12 +48,19 @@
|
|
| 48 |
"eos_token": "[SEP]",
|
| 49 |
"extra_special_tokens": {},
|
| 50 |
"mask_token": "[MASK]",
|
|
|
|
| 51 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 52 |
"pad_token": "[PAD]",
|
|
|
|
|
|
|
| 53 |
"sep_token": "[SEP]",
|
| 54 |
"sp_model_kwargs": {},
|
| 55 |
"split_by_punct": false,
|
|
|
|
| 56 |
"tokenizer_class": "DebertaV2Tokenizer",
|
|
|
|
|
|
|
| 57 |
"unk_token": "[UNK]",
|
| 58 |
"vocab_type": "spm"
|
| 59 |
}
|
|
|
|
| 48 |
"eos_token": "[SEP]",
|
| 49 |
"extra_special_tokens": {},
|
| 50 |
"mask_token": "[MASK]",
|
| 51 |
+
"max_length": 512,
|
| 52 |
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_to_multiple_of": null,
|
| 54 |
"pad_token": "[PAD]",
|
| 55 |
+
"pad_token_type_id": 0,
|
| 56 |
+
"padding_side": "right",
|
| 57 |
"sep_token": "[SEP]",
|
| 58 |
"sp_model_kwargs": {},
|
| 59 |
"split_by_punct": false,
|
| 60 |
+
"stride": 0,
|
| 61 |
"tokenizer_class": "DebertaV2Tokenizer",
|
| 62 |
+
"truncation_side": "right",
|
| 63 |
+
"truncation_strategy": "longest_first",
|
| 64 |
"unk_token": "[UNK]",
|
| 65 |
"vocab_type": "spm"
|
| 66 |
}
|