Upload tokenizer
Browse files- tokenizer_config.json +7 -0
tokenizer_config.json
CHANGED
|
@@ -13,12 +13,19 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
| 16 |
"model_max_length": 1024,
|
|
|
|
| 17 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
| 18 |
"sep_token": "</s>",
|
| 19 |
"sp_model_kwargs": {},
|
| 20 |
"src_lang": null,
|
|
|
|
| 21 |
"tgt_lang": null,
|
| 22 |
"tokenizer_class": "NllbTokenizer",
|
|
|
|
|
|
|
| 23 |
"unk_token": "<unk>"
|
| 24 |
}
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"max_length": 128,
|
| 17 |
"model_max_length": 1024,
|
| 18 |
+
"pad_to_multiple_of": null,
|
| 19 |
"pad_token": "<pad>",
|
| 20 |
+
"pad_token_type_id": 0,
|
| 21 |
+
"padding_side": "right",
|
| 22 |
"sep_token": "</s>",
|
| 23 |
"sp_model_kwargs": {},
|
| 24 |
"src_lang": null,
|
| 25 |
+
"stride": 0,
|
| 26 |
"tgt_lang": null,
|
| 27 |
"tokenizer_class": "NllbTokenizer",
|
| 28 |
+
"truncation_side": "right",
|
| 29 |
+
"truncation_strategy": "longest_first",
|
| 30 |
"unk_token": "<unk>"
|
| 31 |
}
|