legal-xlm-longformer-base / tokenizer_config.json
joelniklaus's picture
Training in progress, step 10000
2e3c552
{
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": "<mask>",
"model_max_length": 4096,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<unk>"
}