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.

Sign up for GitHub

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

Jump to bottom

PaddleMix 怎么更改多模态模型的Vision encoder呢？ #583

Open

ApolloRay opened this issue Jun 25, 2024 · 1 comment

Assignees

ApolloRay commented Jun 25, 2024

而且权重写在一个pdparams里，无法单独替换视觉编码器或者LM decoder部分的权重。另外貌似生态支持的vision encoder不太多？

paddle-bot bot assigned nemonameless

Collaborator

jerrywgz commented Jul 22, 2024

感谢反馈，目前多模态模型支持的vision encoder数量比较少，另外替换不同vision encoder和LLM部分权重现在还只有BLIP2支持会持续加强

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment