SentenceSplitter-it-en / tokenizer_config.json
LorenzoVentrone's picture
Upload tokenizer
225370a verified
raw
history blame contribute delete
421 Bytes
{
"add_prefix_space": true,
"backend": "tokenizers",
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"is_local": true,
"mask_token": "<mask>",
"max_length": 512,
"model_max_length": 512,
"pad_token": "<pad>",
"sep_token": "</s>",
"stride": 0,
"tokenizer_class": "XLMRobertaTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>"
}