tokenizer_config.json

{
  "additional_special_tokens": [
    "<|endoftext|>",
    "[MASK]",
    "[gMASK]",
    "[sMASK]",
    "<sop>",
    "<eop>",
    "<|system|>",
    "<|user|>",
    "<|assistant|>",
    "<|observation|>",
    "<|begin_of_image|>",
    "<|end_of_image|>",
    "<|begin_of_video|>",
    "<|end_of_video|>",
    "<|begin_of_audio|>",
    "<|end_of_audio|>",
    "<|begin_of_transcription|>",
    "<|end_of_transcription|>"
  ],
  "backend": "tokenizers",
  "clean_up_tokenization_spaces": false,
  "do_lower_case": false,
  "eos_token": "<|endoftext|>",
  "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|>",
    "<|begin_of_audio|>",
    "<|end_of_audio|>",
    "<|begin_of_transcription|>",
    "<|end_of_transcription|>"
  ],
  "is_local": true,
  "model_max_length": 128000,
  "model_specific_special_tokens": {},
  "pad_token": "<|endoftext|>",
  "padding_side": "left",
  "remove_space": false,
  "tokenizer_class": "TokenizersBackend",
  "tool_parser_type": "glm47"
}