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_box|>",
    "<|end_of_box|>",
    "<|sep|>",
    "<|image|>",
    "<|video|>",
    "<think>",
    "</think>",
    "<answer>",
    "</answer>"
  ],
  "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_box|>",
    "<|end_of_box|>",
    "<|sep|>",
    "<|image|>",
    "<|video|>",
    "<think>",
    "</think>",
    "<answer>",
    "</answer>"
  ],
  "is_local": true,
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 64000,
  "model_specific_special_tokens": {},
  "pad_token": "<|endoftext|>",
  "padding_side": "left",
  "processor_class": "Glm4vProcessor",
  "remove_space": false,
  "tokenizer_class": "TokenizersBackend"
}