ce-esci-MiniLM-L12-v2 / tokenizer_config.json
shuttie's picture
initial commit
103bfab
raw
history blame contribute delete
516 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/home/shutty/.cache/huggingface/hub/models--cross-encoder--ms-marco-MiniLM-L-12-v2/snapshots/97f7dcbdd6ab58fe7f44368c795fc5200b48fcbe/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}