Git Product home page Git Product logo

Comments (8)

ZhengHanying avatar ZhengHanying commented on June 26, 2024

请问一下您这边是多卡微调的吗?

from qwen-vl.

InvincibleMinions avatar InvincibleMinions commented on June 26, 2024

请问一下您这边是多卡微调的吗?

不是,是单卡,现在倒是修好了,好像是环境的问题,不过不知道怎么回事adapter_model.bin现在从四百多M变成两百多M了,但是模型效果好像没变化

from qwen-vl.

ybshaw avatar ybshaw commented on June 26, 2024

请问一下您这边是多卡微调的吗?

不是,是单卡,现在倒是修好了,好像是环境的问题,不过不知道怎么回事adapter_model.bin现在从四百多M变成两百多M了,但是模型效果好像没变化

请问下单卡多大的显存才能跑的动微调呢,我单机4卡,共90G的显存,不管是用loar还是qlora,以及分布式还是单机都一直报OOM

from qwen-vl.

InvincibleMinions avatar InvincibleMinions commented on June 26, 2024

请问一下您这边是多卡微调的吗?

不是,是单卡,现在倒是修好了,好像是环境的问题,不过不知道怎么回事adapter_model.bin现在从四百多M变成两百多M了,但是模型效果好像没变化

请问下单卡多大的显存才能跑的动微调呢,我单机4卡,共90G的显存,不管是用loar还是qlora,以及分布式还是单机都一直报OOM

我这里是单卡跑,单卡跑千问7B的lora的话,显存占用和finetune_lora_single_gpu.sh文件中的model_max_length参数有关,参数值越大显存占用越大,我这里参数值384,显存占用24G,参数值2048,显存占用45G

from qwen-vl.

ybshaw avatar ybshaw commented on June 26, 2024

请问一下您这边是多卡微调的吗?

不是,是单卡,现在倒是修好了,好像是环境的问题,不过不知道怎么回事adapter_model.bin现在从四百多M变成两百多M了,但是模型效果好像没变化

请问下单卡多大的显存才能跑的动微调呢,我单机4卡,共90G的显存,不管是用loar还是qlora,以及分布式还是单机都一直报OOM

我这里是单卡跑,单卡跑千问7B的lora的话,显存占用和finetune_lora_single_gpu.sh文件中的model_max_length参数有关,参数值越大显存占用越大,我这里参数值384,显存占用24G,参数值2048,显存占用45G

降低length之后,直接报tensor错误了,请问有遇到吗,数据集也是直接用的官方的,就那两张图片,batch_size也是1,按理不会出现这种错误: RuntimeError: stack expects each tensor to be equal size, but got [1] at entry 0 and [0] at entry 2

from qwen-vl.

KDD2018 avatar KDD2018 commented on June 26, 2024

我也降低了model_max_length,不过是基于chat模型在2张3090上做lora微调,但是效果很差,我理解应该是没微调visual模块的参数导致的,请问大佬们有微调过visual模块吗?只微调visual模块,需要多少算力?

from qwen-vl.

KhawLiang avatar KhawLiang commented on June 26, 2024

@InvincibleMinions 请问一下你这个问题是怎么解决的。我也是遇到同样的问题。可以提供你解决这个问题的方法吗?😊

from qwen-vl.

songduanxiao avatar songduanxiao commented on June 26, 2024

调用模型IMAGE_SET的这个错误可以参考
#287

@InvincibleMinions 请问一下你这个问题是怎么解决的。我也是遇到同样的问题。可以提供你解决这个问题的方法吗?😊

from qwen-vl.

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.