nlp-xxl-xlm-r-longformer / tokenizer_config.json
helena-balabin's picture
Upload tokenizer
9b7ed30
{
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 4096,
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"special_tokens_map_file": "/home/luna.kuleuven.be/u0150403/.cache/huggingface/hub/models--markussagen--xlm-roberta-longformer-base-4096/snapshots/98bc749a58deebb8811a07a57040a3219277b61f/special_tokens_map.json",
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}