tokenizer_config.json

{
  "backend": "tokenizers",
  "cls_token": "<CLS>",
  "is_local": false,
  "local_files_only": false,
  "mask_token": "<MASK>",
  "max_length": 1024,
  "model_max_length": 1024,
  "model_type": "caelis",
  "organization": "Inserloft Research",
  "pad_token": "<PAD>",
  "padding_side": "right",
  "project": "Caelis Neural Base",
  "sep_token": "<SEP>",
  "stride": 0,
  "tokenizer_class": "TokenizersBackend",
  "truncation_side": "right",
  "truncation_strategy": "longest_first",
  "unk_token": "<UNK>"
}