dfm-sentence-encoder-large / tokenizer_config.json
KennethEnevoldsen's picture
Initial commit
c7392f2
raw
history blame contribute delete
379 Bytes
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "do_basic_tokenize": true, "name_or_path": "chcaa/dfm-encoder-large-v1", "never_split": null, "special_tokens_map_file": null, "tokenizer_class": "BertTokenizer", "model_max_length": 512}