donut-mrz / tokenizer_config.json
adbcode's picture
first draft
e05a1d1
raw
history blame contribute delete
650 Bytes
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "from_slow": true, "name_or_path": "naver-clova-ix/donut-base", "processor_class": "DonutProcessor", "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/8dff5958cbdb9de4188d643398d5d92bebb82976ce97e6f741b4793e21600485.01bf49938a78cb9ef1792abc3a5829ec39a7887935548bf42fd8d76bf07f15d8", "tokenizer_class": "XLMRobertaTokenizer"}