chaii-qa / tokenizer_config.json
mrizalf7's picture
Training in progress, epoch 0
6f4c3f5
raw
history blame
617 Bytes
{
"bos_token": "<s>",
"cls_token": "<s>",
"do_lower_case": false,
"eos_token": "</s>",
"full_tokenizer_file": null,
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"name_or_path": "deepset/xlm-roberta-large-squad2",
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"special_tokens_map_file": "germanQA/saved_models/xlm-roberta-large-squad2/special_tokens_map.json",
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}