Giter VIP home page Giter VIP logo

Comments (12)

sanitizer84 avatar sanitizer84 commented on May 18, 2024 1

我的错误提示和你不一样,但是问题差不多,就是超不到cuda安装路径吧,提示里说了,你要sudo find / -name libcudart.so找到你的cuda所在目录,然后export LD_LIBRARY_PATH=cuda所在目录,这行加到你的~/.bashrc里

from huatuo-llama-med-chinese.

s65b40 avatar s65b40 commented on May 18, 2024

看起来是cuda path的问题,可以尝试排查一下运行infer.py的环境中cuda路径是否有异常

from huatuo-llama-med-chinese.

woshicqy avatar woshicqy commented on May 18, 2024

我也遇到了相同的问题,老哥解决了么?

from huatuo-llama-med-chinese.

woshicqy avatar woshicqy commented on May 18, 2024

问题解决了,你把bitsandbytes那个package uninstall一下就可以了

from huatuo-llama-med-chinese.

moonlight12581 avatar moonlight12581 commented on May 18, 2024

问题解决了,你把bitsandbytes那个package uninstall一下就可以了

我uninstall后报错了。麻了,你的可以跑了吗
f49b7891fd9f078fd9604b95c0a2c50

from huatuo-llama-med-chinese.

woshicqy avatar woshicqy commented on May 18, 2024

可以跑了~

from huatuo-llama-med-chinese.

woshicqy avatar woshicqy commented on May 18, 2024

是这样的,uninstall之后,可以跑infer.py但是训练的时候,load_in_8bit = False。这样的话,我的4090显存就会溢出了。我昨天po了问题,作者也没有解答 #48

from huatuo-llama-med-chinese.

woshicqy avatar woshicqy commented on May 18, 2024

作者可以成功部署了么?

from huatuo-llama-med-chinese.

s65b40 avatar s65b40 commented on May 18, 2024

我的错误提示和你不一样,但是问题差不多,就是超不到cuda安装路径吧,提示里说了,你要sudo find / -name libcudart.so找到你的cuda所在目录,然后export LD_LIBRARY_PATH=cuda所在目录,这行加到你的~/.bashrc里

大概率就是这个问题,github上也有更新,针对可能的版本问题做了优化,大家可以尝试一下

from huatuo-llama-med-chinese.

chencoder1 avatar chencoder1 commented on May 18, 2024

看起来是cuda path的问题,可以尝试排查一下运行infer.py的环境中cuda路径是否有异常

在data/llama_data.json更换了自己的数据后,运行bash ./scripts/finetune.sh然后直接bash ./scripts/infer.sh推理时,是不是使用自己的数据微调后的模型吗?

from huatuo-llama-med-chinese.

s65b40 avatar s65b40 commented on May 18, 2024

看起来是cuda path的问题,可以尝试排查一下运行infer.py的环境中cuda路径是否有异常

在data/llama_data.json更换了自己的数据后,运行bash ./scripts/finetune.sh然后直接bash ./scripts/infer.sh推理时,是不是使用自己的数据微调后的模型吗?

fine-tune后进行infer时,需要修改lora的路径再进行infer

from huatuo-llama-med-chinese.

chencoder1 avatar chencoder1 commented on May 18, 2024

看起来是cuda path的问题,可以尝试排查一下运行infer.py的环境中cuda路径是否有异常

在data/llama_data.json更换了自己的数据后,运行bash ./scripts/finetune.sh然后直接bash ./scripts/infer.sh推理时,是不是使用自己的数据微调后的模型吗?

fine-tune后进行infer时,需要修改lora的路径再进行infer

哥 怎么修改啊?能不能加个微信啊chen2319529093,求求你了哥

from huatuo-llama-med-chinese.

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.