LiLTInvoiceCzechV03 / tokenizer_config.json
TomasFAV's picture
End of training
e9a0058 verified
{
"add_prefix_space": true,
"apply_ocr": false,
"backend": "tokenizers",
"bos_token": "<s>",
"cls_token": "<s>",
"cls_token_box": [
0,
0,
0,
0
],
"eos_token": "</s>",
"errors": "replace",
"is_local": false,
"mask_token": "<mask>",
"max_length": 512,
"model_max_length": 512,
"only_label_first_subword": true,
"pad_to_multiple_of": null,
"pad_token": "<pad>",
"pad_token_box": [
0,
0,
0,
0
],
"pad_token_label": -100,
"pad_token_type_id": 0,
"padding_side": "right",
"sep_token": "</s>",
"sep_token_box": [
0,
0,
0,
0
],
"stride": 128,
"tokenizer_class": "TokenizersBackend",
"trim_offsets": true,
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>"
}