tokenizer_config.json

{
  "additional_special_tokens": null,
  "backend": "tokenizers",
  "bos_token": "<|start|>",
  "clean_up_tokenization_spaces": false,
  "cls_token": "<|cls|>",
  "eos_token": "<|end|>",
  "mask_token": "<|mask|>",
  "model_max_length": 1024,
  "pad_token": "<|pad|>",
  "sep_token": "<|sep|>",
  "tokenizer_class": "PreTrainedTokenizerFast",
  "unk_token": "<|unk|>",
  "model_type": "modernbert",
  "vocab_size": 16384
}