Giter Club home page Giter Club logo

Comments (9)

KMnO4-zx avatar KMnO4-zx commented on August 26, 2024

抱歉,我们的脚本暂时不支持多卡微调,如果您有多卡微调的需求的话,您可以看看另一个优秀的大模型微调项目:LLaMA-Factory

from huanhuan-chat.

surviveMiao avatar surviveMiao commented on August 26, 2024

很高兴收到您的回复,我可以进行单卡微调, 但是我运行咱们的脚本时它自动使用的是多卡,如果我是用单卡的话,应该怎么修改脚本?

from huanhuan-chat.

KMnO4-zx avatar KMnO4-zx commented on August 26, 2024

嗯,是这样的。由于我们的脚本只在单卡的机器上测试过,所以您可以尝试把fine_tune/lora目录下的train.py中第
208和213行中的device_map="auto"修改为device_map="cuda:0"device_map="cuda:7"(这个修改时根据您的报错而修改的,您可以选择现存最大的那张卡)。具体需要修改的代码位置如下图所示:
image
希望能对您有帮助~

from huanhuan-chat.

surviveMiao avatar surviveMiao commented on August 26, 2024

谢谢谢谢! 我晓得了。
还有一个问题就是 我昨天使用咱们项目下huanhuan数据集使用pt2的方法对官方Chatglm2-6b模型进行训练,使用的代码是Chatglm2官方微调的代码, 经过我微调后,我问模型“你是谁”类似的问题,模型不不知道它叫“嬛嬛”,这个问题是因为我是用的训练方式是pt2的原因吗? 很期待您的解答。谢谢

from huanhuan-chat.

KMnO4-zx avatar KMnO4-zx commented on August 26, 2024

由于微调方法不同,模型展现出来的效果也会有差异,对于不同的问题也是这样的。角色对话类微调在我们尝试过很多种微调方法之后,确定lora是最适合的。希望这个回答可以帮到您~

from huanhuan-chat.

KMnO4-zx avatar KMnO4-zx commented on August 26, 2024

如果有更多的问题想要交流的话,可以看我的github主页的联系方式。(加微信也可以,需要通过邮箱添加)

from huanhuan-chat.

surviveMiao avatar surviveMiao commented on August 26, 2024

谢谢!非常感谢您的回答。我已向您发送邮件,添加您为好友。万般感谢!

from huanhuan-chat.

Bryce1010 avatar Bryce1010 commented on August 26, 2024
model = AutoModel.from_pretrained(
            finetune_args.model_path, load_in_8bit=False, trust_remote_code=True
        )
        model = model.to("cuda:0")

可以改成这样,选择特定显卡,或者使用export CUDA_VISIBLE_DEVICES=0

from huanhuan-chat.

surviveMiao avatar surviveMiao commented on August 26, 2024
model = AutoModel.from_pretrained(
            finetune_args.model_path, load_in_8bit=False, trust_remote_code=True
        )
        model = model.to("cuda:0")

可以改成这样,选择特定显卡,或者使用export CUDA_VISIBLE_DEVICES=0

好的,谢谢您的回复!

from huanhuan-chat.

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.