Prophetnet_MedPaper_model / tokenizer_config.json
usakha's picture
Training in progress, step 500
08f5adb
raw
history blame contribute delete
376 Bytes
{
"clean_up_tokenization_spaces": true,
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "ProphetNetTokenizer",
"unk_token": "[UNK]",
"x_sep_token": "[X_SEP]"
}