finetuned_minilm / tokenizer_config.json
marcospiau's picture
MiniLM-L6-H384-uncased-msmarco-tiny-finetune
5ba3ccb
raw
history blame contribute delete
556 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "nreimers/MiniLM-L6-H384-uncased",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--nreimers--MiniLM-L6-H384-uncased/snapshots/3276f0fac9d818781d7a1327b3ff818fc4e643c0/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}