QUESTION: Chinese garbled code problem

[xiaolibuzai-ovo]

Note that the issue tracker is NOT the place for general support.

I deployed a model, but encountered the problem of garbled Chinese, what is the reason? such as:

this is my model.json

{
    "version":1,
    "context_length":2048,
    "model_name":"Llama2-Chinese-7b-Chat",
    "model_lang":[
        "zh"
    ],
    "model_ability":[
        "chat"
    ],
    "model_description":"This is a custom model description.",
    "model_specs":[
        {
            "model_format":"pytorch",
            "model_size_in_billions":7,
            "quantizations":[
                "4-bit",
                "8-bit",
                "none"
            ],
            "model_id":"FlagAlpha/Llama2-Chinese-7b-Chat",
            "model_uri":"file:///home/mingzhi/xInference/FlagAlpha/Llama2-Chinese-7b-Chat"
        }
    ],
    "prompt_style":{
        "style_name":"LLAMA2",
        "system_prompt":"<s>[INST] <<SYS>>\nYou are a helpful AI assistant.\n<</SYS>>\n\n",
        "roles":[
            "[INST]",
            "[/INST]"
        ],
        "intra_message_sep":" ",
        "inter_message_sep":" </s><s>",
        "stop_token_ids":[
            2
        ],
        "stop":[
            "</s>"
        ]
    }
}

this is huggingface url: https://huggingface.co/FlagAlpha/Llama2-Chinese-7b-Chat

[ikun52099]

请问您有Llama2-Chinese-7b-Chat的vocab.txt文件的文件吗