[Bug] 本地大语言llama部署千问模型出错!
Author: coynessCreated Jul 8, 2026Updated Aug 13, 2026
Labelsbug
我的大语言模型是用本地的llama.cpp部署千问3.5的9B的Q4,但是呼唤小智后就报错。显示:260708 22:45:16[0.9.4-SiFuLMConocaQw][core.connection]-ERROR-LLM stream processing error: Error code: 400 - {'error': {'code': 400, 'message': "Unable to generate parser for this template. Automatic parser generation failed: \n------------\nWhile executing CallExpression at line 85, column 32 in source:\n...first %}↵ {{- raise_exception('System message must be at the beginnin...\n ^\nError: Jinja Exception: System message must be at the beginning.", 'type': 'invalid_request_error'}}
️ 环境信息
- 部署方式: ubuntu的docker模式
我问豆包,豆包说是系统提示词的问题,但我改系统提示词好像没什么作用。不知道怎么解决~
Source: xinnan-tech/xiaozhi-esp32-server