tokenizer_config.json

{
  "backend": "tokenizers",
  "bos_token": "<|dit_token_16384|>",
  "clean_up_tokenization_spaces": false,
  "do_lower_case": false,
  "eos_token": "<|dit_token_16385|>",
  "extra_special_tokens": [
    "<|endoftext|>",
    "[MASK]",
    "[gMASK]",
    "[sMASK]",
    "<sop>",
    "<eop>",
    "<|system|>",
    "<|user|>",
    "<|assistant|>",
    "<|observation|>",
    "<|begin_of_image|>",
    "<|end_of_image|>",
    "<|begin_of_video|>",
    "<|end_of_video|>",
    "<|image|>",
    "<|video|>"
  ],
  "grid_bos_token": "<sop>",
  "grid_eos_token": "<eop>",
  "image_token": "<|image|>",
  "is_local": true,
  "local_files_only": false,
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 65536,
  "model_specific_special_tokens": {
    "grid_bos_token": "<sop>",
    "grid_eos_token": "<eop>",
    "image_token": "<|image|>"
  },
  "pad_token": "<|dit_token_16385|>",
  "padding_side": "left",
  "remove_space": false,
  "tokenizer_class": "TokenizersBackend"
}