OTel-Embedding-568M / tokenizer_config.json
farbodtavakkoli's picture
Copy of farbodtavakkoli/OTel-Embedding-568M at 4031f9b
156bf44 verified
Raw History Blame Contribute Delete
407 Bytes
{
"add_prefix_space": true,
"backend": "tokenizers",
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"is_local": false,
"mask_token": "<mask>",
"model_max_length": 8192,
"pad_token": "<pad>",
"padding_side": "right",
"sep_token": "</s>",
"sp_model_kwargs": {},
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}