tokenizer_config.json

{
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_chatglm.ChatGLM4Tokenizer",
      null
    ]
  },
  "added_tokens_decoder": {
    "151329": {
      "content": "<|endoftext|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151330": {
      "content": "[MASK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151331": {
      "content": "[gMASK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151332": {
      "content": "[sMASK]",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151333": {
      "content": "<sop>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151334": {
      "content": "<eop>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151335": {
      "content": "<|system|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151336": {
      "content": "<|user|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151337": {
      "content": "<|assistant|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151338": {
      "content": "<|observation|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151339": {
      "content": "<|begin_of_image|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151340": {
      "content": "<|end_of_image|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151341": {
      "content": "<|begin_of_video|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151342": {
      "content": "<|end_of_video|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": true
    },
    "151343": {
      "content": "<|code_prefix|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "151344": {
      "content": "<|code_middle|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "151345": {
      "content": "<|code_suffix|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    },
    "151346": {
      "content": "<|cursor|>",
      "lstrip": false,
      "normalized": false,
      "rstrip": false,
      "single_word": false,
      "special": false
    }
  },
  "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|>", "<|code_prefix|>", "<|code_middle|>", "<|code_suffix|>", "<|cursor|>"],
  "clean_up_tokenization_spaces": false,
  "do_lower_case": false,
  "eos_token": "<|endoftext|>",
  "pad_token": "<|endoftext|>",
  "model_max_length": 1000000000000000019884624838656,
  "padding_side": "left",
  "remove_space": false,
  "tokenizer_class": "ChatGLM4Tokenizer"
}