en-electra-base-sst2 / tokenizer_config.json
gunkaynar's picture
Training in progress, epoch 1
1e0d80e
raw
history blame
424 Bytes
{
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_lower_case": true,
"mask_token": "[MASK]",
"max_length": 64,
"model_max_length": 512,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"stride": 0,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "ElectraTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]"
}