moderation_binary_classification / tokenizer_config.json
Nikitojo's picture
Upload tokenizer
c1a7b18 verified
raw
history blame
646 Bytes
{
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"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": "intfloat/multilingual-e5-large",
"pad_token": "<pad>",
"sep_token": "</s>",
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--intfloat--multilingual-e5-large/snapshots/ab10c1a7f42e74530fe7ae5be82e6d4f11a719eb/special_tokens_map.json",
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}