tokenizer_config.json

{
  "backend": "tokenizers",
  "clean_up_tokenization_spaces": 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|>",
    "<|code_prefix|>",
    "<|code_middle|>",
    "<|code_suffix|>",
    "<think>",
    "</think>",
    "<tool_call>",
    "</tool_call>",
    "<tool_response>",
    "</tool_response>",
    "<arg_key>",
    "</arg_key>",
    "<arg_value>",
    "</arg_value>",
    "/nothink",
    "<|begin_of_box|>",
    "<|end_of_box|>",
    "<|image|>",
    "<|video|>"
  ],
  "is_local": true,
  "model_max_length": 655380,
  "pad_token": "<|endoftext|>",
  "padding_side": "left",
  "processor_class": "GlmOcrProcessor",
  "tokenizer_class": "TokenizersBackend"
}