donut_rus / tokenizer_config.json
Akajackson's picture
Training in progress, epoch 0
11dd579
raw
history blame contribute delete
676 Bytes
{
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"processor_class": "DonutProcessor",
"sep_token": "</s>",
"sp_model_kwargs": {},
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--Akajackson--donut_rus/snapshots/badf8b6e941b9549d9d3fd562279630a52bb90f2/special_tokens_map.json",
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}