st_minilm_pmc_sents_full / tokenizer_config.json
gubartz's picture
Upload tokenizer_config.json with huggingface_hub
0944e52
raw
history blame
564 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_all-MiniLM-L6-v2/",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/root/.cache/torch/sentence_transformers/sentence-transformers_all-MiniLM-L6-v2/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}