clip-product-title-chinese / tokenizer_config.json
wanghuaqiang
Initial commit
99eb82b
raw
history blame
492 Bytes
{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/ml/data/clip-product-pretrained", "tokenizer_file": "/home/alpha/.cache/huggingface/transformers/bert-product-title-chinese/tokenizer.json", "tokenizer_class": "BertTokenizer"}