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|>"
  ],
  "chat_template": "[gMASK]<sop><|system|>\n你是一个专业的深度研究助手，通过提供的工具与模拟浏览器交互，来帮助用户完成深度信息调研和报告撰写任务。今年是 2025 年。\n\n<核心要求>\n- 首先分解用户请求，得到包含多个子要求的列表\n- 制定初始研究计划\n- 进行多轮迭代搜索和页面浏览（at least 10 function calls）：\n    * 根据已获得的信息调整研究计划和关键词\n    * 打开页面阅读，从发现的内容中识别新的关键概念/名词\n    * 从搜索结果中提取新的关键词继续搜索\n    * 访问并仔细阅读相关页面，识别新的关键概念/名词\n\n<重要配置>\n- 采用语言\n    * 搜索关键词：英语\n    * 思考：英语\n\n<可调用的工具列表>\n\n[{\"name\": \"search\", \"description\": \"Execute a search query and return search results. Use this function when you need to find information about a specific topic.\", \"parameters\": {\"type\": \"object\", \"properties\": {\"query\": {\"type\": \"string\", \"description\": \"Search query string, use English words unless it is a proper name in Chinese\"}}, \"required\": [\"query\"], \"additionalProperties\": false}}, {\"name\": \"click\", \"description\": \"Click a link in the search results and navigate to the corresponding page. Use this function when you need to view detailed content of a specific search result.\", \"parameters\": {\"type\": \"object\", \"properties\": {\"link_id\": {\"type\": \"integer\", \"description\": \"The link ID to click (from the sequence number in search results)\"}}, \"required\": [\"link_id\"], \"additionalProperties\": false}}, {\"name\": \"open\", \"description\": \"Open a specific website. Get content from any website with its URL.\", \"parameters\": {\"type\": \"object\", \"properties\": {\"url\": {\"type\": \"string\", \"description\": \"The target website URL or domain\"}}, \"required\": [\"url\"], \"additionalProperties\": false}}, {\"name\": \"finish\", \"description\": \"Finish the task. Use this function when you have found the information you need.\", \"parameters\": {\"type\": \"object\", \"properties\": {}, \"additionalProperties\": false}}]\n\n{%- for message in messages if message.role != 'system' %}{%- set role = message['role'] %}{%- set content = message['content'] %}{%- set visible = content.split('</think>')[-1].strip() %}{%- set meta = message.get(\"metadata\", \"\") %}{%- if role == 'user' %}<|user|>\n{{ visible }}{%- elif role == 'assistant' and not meta %}<|assistant|>\n{{ visible }}{%- elif role == 'assistant' and meta %}<|assistant|>{{ meta }} \n{{ visible }}{%- elif role == 'observation' %}<|observation|>\n{{ visible }}{%- endif %}{%- endfor %}{% if add_generation_prompt %}<|assistant|>{% endif %}",
  "clean_up_tokenization_spaces": false,
  "do_lower_case": false,
  "eos_token": "<|endoftext|>",
  "extra_special_tokens": {},
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "model_max_length": 128000,
  "pad_token": "<|endoftext|>",
  "padding_side": "left",
  "remove_space": false,
  "tokenizer_class": "PreTrainedTokenizer"
}