Giter Site home page Giter Site logo

Comments (4)

jubgjf avatar jubgjf commented on August 16, 2024

QLoRA中，模型权重不可在4bit精度计算，必须反量化为bf16再计算，所以整体速度会变慢

可以参考HuggingFace的博客以及Google Cloud文档，提到了QLoRA的计算方式和速度问题

from chinese-mixtral-8x7b.

snowlixue avatar snowlixue commented on August 16, 2024

我用的是88G的Chinese-Mixtral-8x7B模型，所以这里面也有QLoRA的权重吗

from chinese-mixtral-8x7b.

jubgjf avatar jubgjf commented on August 16, 2024

88G的Chinese-Mixtral-8x7B模型是【LoRA权重】 + 【原Mixtral-8x7B权重】合并后的模型，精度是bf16，不是单独的QLoRA权重

使用4bit进行加载，就会导致产生额外计算量用于反量化

from chinese-mixtral-8x7b.

snowlixue avatar snowlixue commented on August 16, 2024

了解了，非常感谢

from chinese-mixtral-8x7b.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.