echo-sbert-domain / tokenizer_config.json
aynaval2003's picture
Trained encoder
3eb4652 verified
Raw History Blame Contribute Delete
387 Bytes
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"errors": "replace",
"is_local": true,
"local_files_only": false,
"mask_token": "<mask>",
"model_max_length": 128,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "RobertaTokenizer",
"trim_offsets": true,
"unk_token": "<unk>"
}