TILDEv2-noExp / tokenizer_config.json
ielab's picture
Upload tokenizer_config.json
2273599
raw
history blame
475 Bytes
{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "ckpts_uniCOIL_Ti_noExpansion_bm25_hard/checkpoint-5epoch/", "special_tokens_map_file": "ckpts_uniCOIL_Ti_noExpansion_bm25_hard/checkpoint-5epoch/special_tokens_map.json", "tokenizer_file": null}