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.

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

convert gpt model exceeds maximum protobuf size of 2GB #21

Closed
BinaryUltra opened this issue Jan 11, 2021 · 1 comment
Closed

convert gpt model exceeds maximum protobuf size of 2GB #21

BinaryUltra opened this issue Jan 11, 2021 · 1 comment

Comments

@BinaryUltra
Copy link

image

I encountered error when convert my own model to .pb format which contain 32 encoder layers, how should I get solve the problem.
@Taka152
Copy link
Contributor

Taka152 commented Jan 11, 2021

We haven't supported any big model like GPT3 by now. I recommend finding Protobuf's alternative to solve the limitation of 2GB message size, the related sources are in the proto folder, It would be appreciated if you make a PR.

@Taka152 Taka152 closed this as completed Jan 26, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@Taka152 @BinaryUltra