Training done
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +0 -7
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -849,18 +849,11 @@
|
|
| 849 |
"cls_token": "<s>",
|
| 850 |
"eos_token": "</s>",
|
| 851 |
"mask_token": "<mask>",
|
| 852 |
-
"max_length": 768,
|
| 853 |
"model_max_length": 1000000000000000019884624838656,
|
| 854 |
-
"pad_to_multiple_of": null,
|
| 855 |
"pad_token": "<pad>",
|
| 856 |
-
"pad_token_type_id": 0,
|
| 857 |
-
"padding_side": "right",
|
| 858 |
"processor_class": "DonutProcessor",
|
| 859 |
"sep_token": "</s>",
|
| 860 |
"sp_model_kwargs": {},
|
| 861 |
-
"stride": 0,
|
| 862 |
"tokenizer_class": "XLMRobertaTokenizer",
|
| 863 |
-
"truncation_side": "right",
|
| 864 |
-
"truncation_strategy": "longest_first",
|
| 865 |
"unk_token": "<unk>"
|
| 866 |
}
|
|
|
|
| 849 |
"cls_token": "<s>",
|
| 850 |
"eos_token": "</s>",
|
| 851 |
"mask_token": "<mask>",
|
|
|
|
| 852 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 853 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
| 854 |
"processor_class": "DonutProcessor",
|
| 855 |
"sep_token": "</s>",
|
| 856 |
"sp_model_kwargs": {},
|
|
|
|
| 857 |
"tokenizer_class": "XLMRobertaTokenizer",
|
|
|
|
|
|
|
| 858 |
"unk_token": "<unk>"
|
| 859 |
}
|