minilm-finutened-dataverse / tokenizer_config.json
dipudl's picture
Training in progress, step 500
7ece1e4
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"name_or_path": "microsoft/MiniLM-L12-H384-uncased",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/root/.cache/huggingface/transformers/1e5909e4dfaa904617797ed35a6105a23daa56cbefca48fef329f772584699fb.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}