ct2fast-e5-small / tokenizer_config.json
michaelfeil's picture
Upload intfloat/e5-small ctranslate fp16 weights
14006c8
raw
history blame
362 Bytes
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "amlt/1109_tnlrv3_bs32k_ft/all_kd_ft", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}