You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
B站:https://www.bilibili.com/video/BV1rPQBYLEF9
简介:
DeepSeek-671b-Q1量化Win10便携整合包V1.1,夸克盘分享,大小136G:https://pan.quark.cn/s/263478283844
下载里面671b的两个分卷包,可放在任意无中文和空格路径的目录
最低支持128G内存+NV12G显卡,但由于该配置效率比较低,只简单开起来了下没做什么测试,有兴趣的朋友可以自行尝试
64G内存如果有比较快的NVME固态可以设100G虚拟内存试试,有一定几率可以用起来
最新建议:核心数填四分之三左右;Q2-Q4量化模型也可以运行,只需自行下载模型文件后替换整合包文件即可
整合包仅供测试,Win10下的效能比Linux有一定的差距【尤其是上下文长度上】,需要部署的尽量使用Linux
需要单独设置max_new_tokens和cache_lens两个参数可以在运行菜单输入lcdf跳转高级设置菜单进行配置
建议了解这两个参数含义的朋友测试,否则直接运行菜单选择选项运行即可
Beta Was this translation helpful? Give feedback.
All reactions