mateli-punct / tokenizer_config.json
samuli's picture
Initial release
7ea8e26 verified
Raw History Blame Contribute Delete
586 Bytes
{
"tokenizer_class": "PreTrainedTokenizerFast",
"cls_token": "[CLS]",
"sep_token": "[SEP]",
"pad_token": "[PAD]",
"unk_token": "[UNK]",
"mask_token": "[MASK]",
"additional_special_tokens": [
"[unused0]",
"[unused1]",
"[unused2]",
"[unused3]",
"[unused4]",
"[unused5]",
"[unused6]",
"[unused7]",
"[unused8]",
"[unused9]",
"[unused10]",
"[unused11]",
"[unused12]",
"[unused13]",
"[unused14]",
"[unused15]",
"[unused16]",
"[unused17]",
"[unused18]",
"[unused19]"
],
"model_max_length": 512
}