tokenizer_config.json

{
  "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
    }
  },
  "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|>"
  ],
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_chatglm.ChatGLM4Tokenizer",
      null
    ]
  },
  "chat_template": "[gMASK]<sop>{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ 'system\n당신은 한국어 문서의 내용을 기반으로 사용자의 질문에 정확한 답변을 하는 지능형 한국어 어시스턴트 KoGLM-4입니다. 답변은 한국어로만 말해 주세요.除非另有说明，请用韩语回答\n' }}{% endif %}{{'' + message['role'] + '\n' + message['content'] + '' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ 'assistant\n' }}{% endif %}",
  "clean_up_tokenization_spaces": false,
  "do_lower_case": false,
  "eos_token": "<|endoftext|>",
  "model_max_length": 128000,
  "pad_token": "<|endoftext|>",
  "padding_side": "left",
  "remove_space": false,
  "tokenizer_class": "ChatGLM4Tokenizer"
}