Splade_PP_en_v2 / tokenizer_config.json
Prithivi Da
Initial Commit
1cdf444
raw
history blame
No virus
497 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "Luyu/co-condenser-marco",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/bos/tmp0/luyug/outputs/condenser/models/l2-s6-km-L128-e8-lr1e-4-b256/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}