KoSimCSE-roberta-multitask / tokenizer_config.json
BM-K's picture
add tokenizer
dc9728c
raw
history blame contribute delete
599 Bytes
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "do_basic_tokenize": true, "never_split": null, "bos_token": "[CLS]", "eos_token": "[SEP]", "model_max_length": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/9d0c87e44b00acfbfbae931b2e4068eb6311a0c3e71e23e5400bdf57cab4bfbf.70c17d6e4d492c8f24f5bb97ab56c7f272e947112c6faf9dd846da42ba13eb23", "name_or_path": "output/kor_sts_BM-K-KoSimCSE-roberta/", "tokenizer_class": "BertTokenizer"}