-
Notifications
You must be signed in to change notification settings - Fork 966
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
Odd behaviour with GPT2 after bfc6d42 #385
Comments
I can reproduce the issue and confirm that bfc6d42 is the cause. We should fix this |
Thank you very much for spotting this regression! Hope I manage to implement a better CI soon and be able to catch such bugs earlier. |
Ah, thanks for finding the source of the bug. By the way, I found this because my own unit tests were failing :) . But I'd be happy to contribute some testing stuff into GGML. There's a related issue for that, see #344 . |
@smspillaz : @ggerganov just merged this PR. Would be happy to coordinate efforts! |
New behaviour after bfc6d42
Old behaviour at bfc6d42^
I haven't been able to figure out exactly why this happens, but I did bisect it down to that commit. One thing I noticed when poking around in the debugger is that the logits for the first predicted token are correct, but the logits for the second predicted token differ.
The text was updated successfully, but these errors were encountered: