all-MiniLM-L6-v2-quora / tokenizer_config.json
rohit1998's picture
Training in progress, epoch 1
f2eb145
raw
history blame
593 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/home/ubuntu/.cache/huggingface/transformers/828163b9cc16a2e7d13324e55d0bc0433dab54d1ae271e02d2e3cb1387e1135b.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}