my_awesome_model / tokenizer_config.json
koreadaeil's picture
Training in progress, epoch 1
d877917
raw
history blame
470 Bytes
{
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_lower_case": false,
"keep_accents": true,
"mask_token": {
"__type": "AddedToken",
"content": "[MASK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"pad_token": "<pad>",
"remove_space": true,
"sep_token": "[SEP]",
"sp_model_kwargs": {},
"tokenizer_class": "FNetTokenizer",
"unk_token": "<unk>"
}