tokenizer_config.json

{
  "backend": "tokenizers",
  "clean_up_tokenization_spaces": false,
  "document_token": "<doc>",
  "eos_token": "<eos>",
  "extra_special_tokens": [],
  "image_token": "<img>",
  "mask_token": "<mask>",
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 16384,
  "pad_token": "<pad>",
  "processor_class": "NeoMMEProcessor",
  "query_token": "<query>",
  "row_token": "<row>",
  "tokenizer_class": "TokenizersBackend",
  "unk_token": "<unk>"
}