sentence-bert-swedish-cased / tokenizer_config.json
Lauler's picture
v2.0 with teacher all-mpnet-base-v2, trained with longer paragraphs
a65f4bc
raw
history blame
614 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"name_or_path": "output/no-normalize-en-sv-2022-12-26_18-39-42/",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/ceph/hpc/home/eufatonr/.cache/huggingface/hub/models--KB--bert-base-swedish-cased/snapshots/81c7baa04742a30cb6732c181e678721868cb42e/special_tokens_map.json",
"strip_accents": false,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}