Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +22 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"do_lower_case": true,
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"mask_token": "<mask>",
|
| 8 |
+
"max_length": 250,
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
+
"pad_to_multiple_of": null,
|
| 11 |
+
"pad_token": "<pad>",
|
| 12 |
+
"pad_token_type_id": 0,
|
| 13 |
+
"padding_side": "right",
|
| 14 |
+
"sep_token": "</s>",
|
| 15 |
+
"stride": 0,
|
| 16 |
+
"strip_accents": null,
|
| 17 |
+
"tokenize_chinese_chars": true,
|
| 18 |
+
"tokenizer_class": "MPNetTokenizer",
|
| 19 |
+
"truncation_side": "right",
|
| 20 |
+
"truncation_strategy": "longest_first",
|
| 21 |
+
"unk_token": "[UNK]"
|
| 22 |
+
}
|