trec_covid_synthetic / tokenizer_config.json
bergum's picture
Upload tokenizer
19327c2
raw
history blame
538 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "./model/",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--cross-encoder--ms-marco-MiniLM-L-6-v2/snapshots/b2cfda50a1a9fc7919e7444afbb52610d268af92/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}