is this actually working?

[fblgit]

did anyone made this to work?

i tested half dozen of models.. none of them actually worked.

Upvote & Fund

• We're using Polar.sh so you can upvote and help fund this issue.
• We receive the funding once the issue is completed & confirmed by you.
• Thank you in advance for helping prioritize & fund our backlog.

[kyegomez]

@fblgit what does this mean? Can you elaborate?

[fblgit]

i couldnt get many of the models around to work, did u manage to get this to train and do inference properly? or this is some experimental non-working code/experiment/test/poc?

[Ronsor]

did anyone made this to work?

i tested half dozen of models.. none of them actually worked.

No, this code does not work.

[dmarx]

Do any of this user's repositories?

[kyegomez]

i couldnt get many of the models around to work, did u manage to get this to train and do inference properly? or this is some experimental non-working code/experiment/test/poc?

what code did you run, give me errors, or the output.

Also you need to finetune the model before this works so you know.

[kyegomez]

did anyone made this to work? i tested half dozen of models.. none of them actually worked.

No, this code does not work.

do you have an error? please post the error

[kyegomez]

Do any of this user's repositories?

what error do you have exactly?

[suzuke]

The implementation of this binear is completely wrong, not only does it not follow the process outlined in the Bitnet paper, but it also misunderstands all the computational principles. I don't understand why it still receives so many stars.

[suzuke]

The issues I mentioned have been addressed in the commit 6cdb2ea998e843b454f2fbaaef73bc6bf92c305f.

[kyegomez]

@suzuke if it's wrong please submit a pull request

[github-actions[bot]]

Stale issue message