Uploading tokenizer
Browse files- tokenizer_config.json +7 -0
tokenizer_config.json
CHANGED
|
@@ -1868,12 +1868,19 @@
|
|
| 1868 |
"extra_special_tokens": {},
|
| 1869 |
"legacy_behaviour": false,
|
| 1870 |
"mask_token": "<mask>",
|
|
|
|
| 1871 |
"model_max_length": 1024,
|
|
|
|
| 1872 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
| 1873 |
"sep_token": "</s>",
|
| 1874 |
"sp_model_kwargs": {},
|
| 1875 |
"src_lang": "eng_Latn",
|
|
|
|
| 1876 |
"tgt_lang": null,
|
| 1877 |
"tokenizer_class": "NllbTokenizer",
|
|
|
|
|
|
|
| 1878 |
"unk_token": "<unk>"
|
| 1879 |
}
|
|
|
|
| 1868 |
"extra_special_tokens": {},
|
| 1869 |
"legacy_behaviour": false,
|
| 1870 |
"mask_token": "<mask>",
|
| 1871 |
+
"max_length": 1024,
|
| 1872 |
"model_max_length": 1024,
|
| 1873 |
+
"pad_to_multiple_of": null,
|
| 1874 |
"pad_token": "<pad>",
|
| 1875 |
+
"pad_token_type_id": 0,
|
| 1876 |
+
"padding_side": "right",
|
| 1877 |
"sep_token": "</s>",
|
| 1878 |
"sp_model_kwargs": {},
|
| 1879 |
"src_lang": "eng_Latn",
|
| 1880 |
+
"stride": 0,
|
| 1881 |
"tgt_lang": null,
|
| 1882 |
"tokenizer_class": "NllbTokenizer",
|
| 1883 |
+
"truncation_side": "right",
|
| 1884 |
+
"truncation_strategy": "longest_first",
|
| 1885 |
"unk_token": "<unk>"
|
| 1886 |
}
|