miniLM-test / tokenizer_config.json
jn2clark's picture
Upload 6 files
7cc42ad
raw
history blame contribute delete
638 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"name_or_path": "flax-sentence-embeddings/all_datasets_v4_MiniLM-L6",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/home/ukp-reimers/.cache/huggingface/transformers/1e5909e4dfaa904617797ed35a6105a23daa56cbefca48fef329f772584699fb.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}