indonesian-punctuation / tokenizer_config.json
Wikidepia's picture
Initial ALBERT Tiny model
638025d
{"do_lower_case": false, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": "/root/.cache/huggingface/transformers/61e11849a832cf0858036414a754a64d65c79963006b95a39f8051e1577b322a.15ed5b79b197b4fcc5f3f80b2ee89a5a3ad708dbd076575cd22cffd9e1a56284", "name_or_path": "malay-huggingface/albert-tiny-bahasa-cased", "tokenizer_class": "AlbertTokenizer"}