[GET HELP] How to disable Thinking in Ollama? (/set nothink) 如何关闭Ollama下的思考?
1. Checklist / 检查项
[√] I have removed sensitive information from configuration/logs.
我已移除配置或日志中的敏感信息。
[√] I have checked the FAQ and existing issues.
[√] I am using the latest version of the project.
我正在使用项目的最新版本。
2. Environment Details / 环境信息
How did you install Open-LLM-VTuber:
你是如何安装 Open-LLM-VTuber 的:
- git clone (源码克隆)
- release zip (发布包)
- [√] exe (Windows) (Windows 安装包)
- dmg (MacOS) (MacOS 安装包)
Are you running the backend and frontend on the same device?
后端和前端是否在同一台设备上运行?
Yes/是的
If you used GPU, please provide your GPU model and driver version:
如果你使用了 GPU,请提供你的 GPU 型号及驱动版本信息:
Nvidia 5080 610.88 (CUDA 12.9.2_576.57)
Browser (if applicable):
浏览器(如果适用):Chrome
3. Describe the bug / 问题描述
What exactly is happening? What do you want to see? How to reproduce?
请详细描述发生了什么、你希望看到什么,以及如何复现。
Ollama keep thinking on Ollama Qwen3.8:27b, which cause bad chat experience. Ollama收到指令后会尝试Thinking,导致对话非常缓慢体验很差。
4. Screenshots / Logs (if relevant)
截图 / 日志(如有)
- Backend log: 后端日志
- Frontend setting (General): 前端设置(通用)
- Frontend console log (F12): 前端控制台日志(F12)
- If using Ollama: output of
ollama ps: 如果使用 Ollama,请附上ollama ps的输出
Tried use /set nothink , work perfectly on cli.
我试过在控制台对话中输入 /set nothink ,可以做到不思考直接回答。
5. Configuration / 配置文件
Please provide relevant config files, with sensitive info like API keys removed
请提供相关配置文件(请务必去除 API key 等敏感信息)
conf.yamlmodel_dict.json,.model3.json
I only changed "model" in Ollama settings. Config中我只设置了Ollama的Model。
Source: Open-LLM-VTuber/Open-LLM-VTuber