Giter VIP home page Giter VIP logo

Comments (4)

w5688414 avatar w5688414 commented on June 11, 2024

请问你们是什么场景,为什么不能内存扩大一点呢?

from paddlenlp.

ShawnNew avatar ShawnNew commented on June 11, 2024

请问你们是什么场景,为什么不能内存扩大一点呢?

假设不能保证用户测试主机内存足够加载一定模型,上述错误导致程序异常推出,没有足够多的信息定位。

期望或许可以从两个方面解决:

  1. 优化权重加载的逻辑
  2. 给出正确的报错信息,引导用户调试

from paddlenlp.

DrownFish19 avatar DrownFish19 commented on June 11, 2024

请问你们是什么场景,为什么不能内存扩大一点呢?

假设不能保证用户测试主机内存足够加载一定模型,上述错误导致程序异常推出,没有足够多的信息定位。

期望或许可以从两个方面解决:

  1. 优化权重加载的逻辑
  2. 给出正确的报错信息,引导用户调试

paddlenlp中已经尽可能优化了权重加载过程,但是目前大模型套件更加关注加载效率,因此采用了多线程加载的方式实现。如果期望单独加载,可以考虑增加线程顺序控制,按照顺序加载模型,将内存需求降低为一份模型的大小。

from paddlenlp.

ZHUI avatar ZHUI commented on June 11, 2024

你好,可以使用 加载 safetensors 格式的模型,可以避免此问题

from paddlenlp.

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.