We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
在modelscope部署测试了7b、72b 的dpo模型,客户端在windows和mac也都做了测试,极高概率会遇到模型输出的坐标异常,并且一旦发生无法恢复。可用性非常低。其实从分析和动作来看,理解和规划、定位能力还是挺强的,但是几乎必现操作参数返回异常。是否模型本身有问题,还是modelscope的推理框架有问题?
The text was updated successfully, but these errors were encountered:
我们在本地推理的时候没有观察到类似情况,建议优先确认推理框架的问题
Sorry, something went wrong.
我试验了各种方法,也在本地V10卡+vllm部署测试了,依然是几乎必现的,验证指令(win):“在桌面上新建文本文档”。 同样的配置部署sft模型没有这个问题,dpo模型7b和72b都会出现输出异常:
能否提供一下您的vllm和cuda版本以及GPU型号,还有启动推理框架的详细参数?
麻烦把你的复现流程发一下看看?方便包括对应的桌面截图?
No branches or pull requests
在modelscope部署测试了7b、72b 的dpo模型,客户端在windows和mac也都做了测试,极高概率会遇到模型输出的坐标异常,并且一旦发生无法恢复。可用性非常低。其实从分析和动作来看,理解和规划、定位能力还是挺强的,但是几乎必现操作参数返回异常。是否模型本身有问题,还是modelscope的推理框架有问题?
The text was updated successfully, but these errors were encountered: