SCT-KD-BGE-M3-model-phayathaibert / tokenizer_config.json
kornwtp's picture
Initial commit
74f90f1 verified
raw
history blame contribute delete
587 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"}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED", "<_>"], "clean_up_tokenization_spaces": true, "model_max_length": 510, "sp_model_kwargs": {}, "special_tokens_map_file": "../ConGen-Thai/phayathaibert/special_tokens_map.json", "name_or_path": "../ConGen-Thai/phayathaibert", "tokenizer_class": "CamembertTokenizer"}