kogpt2_small / tokenizer_config.json
MrBananaHuman's picture
Upload tokenizer_config.json
3780b9c
raw
history blame
271 Bytes
{
"do_lower_case": false,
"remove_space": true,
"keep_accents": false,
"bos_token": "<s>",
"eos_token": "</s>",
"unk_token": "<unk>",
"pad_token": "<pad>",
"additional_special_tokens": null,
"sp_model_kwargs": {},
"tokenizer_class": "XLNetTokenizer"
}