Upload tokenizer
Browse files- tokenizer_config.json +7 -0
tokenizer_config.json
CHANGED
|
@@ -1884,12 +1884,19 @@
|
|
| 1884 |
"extra_special_tokens": {},
|
| 1885 |
"legacy_behaviour": false,
|
| 1886 |
"mask_token": "<mask>",
|
|
|
|
| 1887 |
"model_max_length": 1024,
|
|
|
|
| 1888 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
| 1889 |
"sep_token": "</s>",
|
| 1890 |
"sp_model_kwargs": {},
|
| 1891 |
"src_lang": "eng_Latn",
|
|
|
|
| 1892 |
"tgt_lang": null,
|
| 1893 |
"tokenizer_class": "NllbTokenizer",
|
|
|
|
|
|
|
| 1894 |
"unk_token": "<unk>"
|
| 1895 |
}
|
|
|
|
| 1884 |
"extra_special_tokens": {},
|
| 1885 |
"legacy_behaviour": false,
|
| 1886 |
"mask_token": "<mask>",
|
| 1887 |
+
"max_length": 256,
|
| 1888 |
"model_max_length": 1024,
|
| 1889 |
+
"pad_to_multiple_of": null,
|
| 1890 |
"pad_token": "<pad>",
|
| 1891 |
+
"pad_token_type_id": 0,
|
| 1892 |
+
"padding_side": "right",
|
| 1893 |
"sep_token": "</s>",
|
| 1894 |
"sp_model_kwargs": {},
|
| 1895 |
"src_lang": "eng_Latn",
|
| 1896 |
+
"stride": 0,
|
| 1897 |
"tgt_lang": null,
|
| 1898 |
"tokenizer_class": "NllbTokenizer",
|
| 1899 |
+
"truncation_side": "right",
|
| 1900 |
+
"truncation_strategy": "longest_first",
|
| 1901 |
"unk_token": "<unk>"
|
| 1902 |
}
|