bi-encoder_msmarco_bert-base_german / tokenizer_config.json
PM-AI's picture
Add new SentenceTransformer model.
65ab0e5
raw history blame
No virus
451 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"max_len": 512,
"name_or_path": "models/bi-encoder_mmarco-google-german_margin-mse_gbert-base_bs75-epochs10/",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": null,
"strip_accents": false,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}