Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +27 -0
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "[CLS]",
|
| 5 |
+
"cls_token": "[CLS]",
|
| 6 |
+
"do_lower_case": false,
|
| 7 |
+
"eos_token": "[SEP]",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"[PAD]",
|
| 10 |
+
"[CLS]",
|
| 11 |
+
"[SEP]"
|
| 12 |
+
],
|
| 13 |
+
"is_local": true,
|
| 14 |
+
"mask_token": "[MASK]",
|
| 15 |
+
"max_length": 256,
|
| 16 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 17 |
+
"pad_token": "[PAD]",
|
| 18 |
+
"sep_token": "[SEP]",
|
| 19 |
+
"split_by_punct": false,
|
| 20 |
+
"stride": 0,
|
| 21 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 22 |
+
"truncation_side": "right",
|
| 23 |
+
"truncation_strategy": "longest_first",
|
| 24 |
+
"unk_id": 3,
|
| 25 |
+
"unk_token": "[UNK]",
|
| 26 |
+
"vocab_type": "spm"
|
| 27 |
+
}
|