ConGen-Multilingual-MiniLM-L12 / tokenizer_config.json
kornwtp's picture
Initial commit
ca2d86d
raw
history blame
543 Bytes
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": "/ist/users/wuttikornp/.cache/torch/sentence_transformers/microsoft_Multilingual-MiniLM-L12-H384/special_tokens_map.json", "name_or_path": "pretrianed_models/Multilingual-MiniLM-L12-H384", "sp_model_kwargs": {}, "tokenizer_class": "XLMRobertaTokenizer"}