-
Notifications
You must be signed in to change notification settings - Fork 493
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
🤗 transformers compatibility issues #178
Comments
Hi! Thanks for the detailed report.
So, are there specific properties in |
Thanks for the quick answer! Sounds good for Regarding the return dictionary, in principle, having the sequences would already mean enabling most gradient/occlusion-based methods. Attention attribution is actively being developed in Inseq, so being able to extract attention scores would also be great to enable such methods, but I understand that it might be problematic in terms of inference speed. Apart from those, other properties would likely not be used anytime soon. |
attention mask: #206 |
Hello,
I'm trying to make the
DistributedBloomForCausalLM
work with our libraryinseq
to extract feature attributions from BLOOM generations. However, at the moment I am facing some issues that prevent me from using the distributed model:model.generate
by passing thereturn_dict_in_generate=True
argument, as supported by HuggingFace. In your current implementation, there doesn't seem to be a way to extract such outputs, so when we access the propertysequences
an exception is thrown. To reproduce:model.attribute
as:I get the following error:
Correct me if I'm wrong, but I believe both
return_dict_in_generate
andattention_mask
support should be achievable for thepetals
implementation, right? Would you consider supporting such usage? Thanks in advance! 🙂The text was updated successfully, but these errors were encountered: