-
Notifications
You must be signed in to change notification settings - Fork 2.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
用两张4090微调13b的belle出现oom,单卡则不会 #24
Comments
多卡需要每张卡都有 24G 内存。 |
Dalao,单卡我这里也有个问题,13b的模型我4bit量化,输入512输出512怎么微调也OOM o(╥﹏╥)o |
GPU 的空闲显存有多少? |
降低了可以。还有个问题 from transformers import LlamaForCausalLM, AutoTokenizer ckpt = './bloom_13b/' 官方的示例对话的结果,对比我用项目里的web demo结果不一致(均为8bit do_sample=False),而且web生成的效果比我用上述官方示例的效果差很多,这是怎么回事? web demo的参数我在后台都改了,如下 |
web demo的回答惜字如金。。 |
已经解决,原来在代码里面,会自动包装问题,导致结果和官方示例不一致,而且还导致回答惜字如金 |
你好,请问怎么修改解决保证该项目与官方回答基本一致? |
@yumulinfeng1 使用指令微调后的模型时候应该在命令行参数中加入 |
我单卡微调没有出现这个情况,多卡出现了,但是我有一张卡已经被占用了15G显存,还剩8g左右,相当于我是8+24g进行多卡微调,这样微调会确实会出现问题?还是我没配置好的问题?
The text was updated successfully, but these errors were encountered: