tokenizer_config.json

{
  "bos_token": {
    "__type": "AddedToken",
    "content": "[BOS]",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "clean_up_tokenization_spaces": true,
  "cls_token": {
    "__type": "AddedToken",
    "content": "[CLS]",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "eos_token": {
    "__type": "AddedToken",
    "content": "[EOS]",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "mask_token": {
    "__type": "AddedToken",
    "content": "[MASK]",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "model_max_length": 2048,
  "pad_token": {
    "__type": "AddedToken",
    "content": "[PAD]",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "sep_token": {
    "__type": "AddedToken",
    "content": "[SEP]",
    "lstrip": false,
    "normalized": true,
    "rstrip": false,
    "single_word": false
  },
  "tokenizer_class": "PerceiverTokenizer"
}