Skip to content
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

FlagEmbedding/inference/reranker/decoder_only/models/gemma_model.py 存在版本问题 #1304

Open
moseshu opened this issue Dec 26, 2024 · 3 comments

Comments

@moseshu
Copy link

moseshu commented Dec 26, 2024

transformers 4.46.0+没有GEMMA2_ATTENTION_CLASSES 这个了,在gemma_model.py 56行 需要把这个去掉

@545999961
Copy link
Collaborator

感谢您的反馈!
考虑到不同版本兼容性不同,这里我们推荐使用4.44.2及以下的transformers版本,去掉GEMMA2_ATTENTION_CLASSES可能导致低版本transformers报错,这里就需要自行更改了

@firezym
Copy link

firezym commented Dec 30, 2024

这个目前用于bge-m3暂时work的

@moseshu
Copy link
Author

moseshu commented Dec 31, 2024

感谢您的反馈! 考虑到不同版本兼容性不同,这里我们推荐使用4.44.2及以下的transformers版本,去掉GEMMA2_ATTENTION_CLASSES可能导致低版本transformers报错,这里就需要自行更改了

我修改了一下,切换成4.47.0版本是一样的效果,在这个模型的效果没啥区别啊,计算内积也是一样的mbge-multilingual-gemma2

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants