jina-embeddings-v2-base-code / tokenizer_config.json
bwang0911's picture
Update tokenizer_config.json
dcc1fee
raw
history blame
493 Bytes
{
"add_prefix_space": false,
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"errors": "replace",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false
},
"model_max_length": 8192,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "RobertaTokenizer",
"trim_offsets": true,
"unk_token": "<unk>"
}