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

Minimal support for Mistral 7B model. #1528

Merged
merged 5 commits into from
Nov 7, 2023
Merged

Conversation

vince62s
Copy link
Member

@minhthuc2502 Maybe check this code

@minhthuc2502
Copy link
Collaborator

minhthuc2502 commented Oct 31, 2023

Hello, Yeah that what I did, but I create more operation for sliding instead of using split. I will push this with chunking of input.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think we need to assign self.sliding_window of spec to be added in model later.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Where is it used later? but yes can't hurt to add it.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think to add a variable into model.bin, the variable sliding_window have to be a member of class spec, if it is not, it will not be added to model in convert process.

@vince62s
Copy link
Member Author

vince62s commented Nov 3, 2023

closing this one, reviewing #1524 with @minhthuc2502 taking into account the input chunking.

@vince62s vince62s closed this Nov 3, 2023
@vince62s vince62s reopened this Nov 6, 2023
@vince62s vince62s changed the title Sliding windows at inference for Mistral Minimal support for Mistral 7B model. Nov 6, 2023
@vince62s vince62s merged commit 50e9ba4 into OpenNMT:master Nov 7, 2023
18 checks passed
funboarder13920 pushed a commit to funboarder13920/CTranslate2 that referenced this pull request Nov 7, 2023
funboarder13920 pushed a commit to funboarder13920/CTranslate2 that referenced this pull request Nov 7, 2023
@vince62s vince62s deleted the sliding branch November 16, 2023 15:05
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

Successfully merging this pull request may close these issues.

2 participants