blog-model-v3 / tokenizer_config.json
scroobiustrip's picture
Add SetFit model
b9338bc
raw
history blame contribute delete
614 Bytes
{
"bos_token": "<s>",
"cls_token": "<s>",
"do_lower_case": true,
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"name_or_path": "/root/.cache/torch/sentence_transformers/sentence-transformers_paraphrase-multilingual-minilm-l12-v2/",
"pad_token": "<pad>",
"sep_token": "</s>",
"special_tokens_map_file": null,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "<unk>"
}