-
Notifications
You must be signed in to change notification settings - Fork 40
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
Map rag model to device in eval rag script #75
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
looks good to me!
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@sagorbrur
Maybe let's add this code snippet here:
Also let's add a comment above this line
rag_model.attach_pre_trained_peft_layers(retriever_peft_model_path, generator_peft_model_path, device)
Something like - "we only wrap this with PEFT layers if there are any ... :
Thanks a lot :)
DALM/dalm/models/rag_e2e_base_model.py
Line 135 in a847640
HI @shamanez ,
The line you refer I am a little bit confused about where to put it. regards |
Hey @sagorbrur is the comment part unclear or is the request to move the code to the specified location unclear? |
Hi @metric-space , Kind regards |
Hi,
According to our discussion on issue #73 , here I have added device mapping in
eval_rag.py
.I have tested and no device mismatch error raising now.
Please have a look and merge if everything is okay.
Thanks and regards