indobert-lite-large-p2-smsa / tokenizer_config.json
tyqiangz's picture
Adding indobert-lite-large-p2 model finetuned on IndoNLU(SmSA)
cfe845b
raw
history blame
552 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, "special_tokens_map_file": "/root/.cache/huggingface/transformers/079b012b9db3ee4852c05e54afd77ca52783f176d619068fe301bdc3fdce319a.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_file": null, "name_or_path": "indobenchmark/indobert-lite-large-p2", "tokenizer_class": "BertTokenizer"}