Michel Nivard

Results 22 comments of Michel Nivard

Is that training of validation loss? and if you generate ±10 texts are they grammatically correct or garbled? I could imagine compression and decompression gets you an almost impressionistic result...

Okay digging into it later today, thanks!

I got the same error. So for me editing `out =` lets the training loop run, but there is generation being outputted at all...

I seem to have got it running thanks!

@LiuChaoXD issue 809 refered to in the response above your comment was merged into mlx main. So mlx now has an SVD and you can implement the galore optimizer in...

> are any documents about how to accelerate SVD by GPU? I found this chapter on parallelising SVD: https://www.irisa.fr/sage/bernard/publis/SVD-Chapter06.pdf

I thought about that, but we post-process the lavaan result, so the standard errors (for example) are off, I don't think I want to expose that to the user to...

Thinking about this more, I might just need to write a separate package for this, based on the bones of gptstudio...

We could make this a potentially powerful tool for people who have disabilities! If we let people voice type code, and it’s transcribe, we can have GPT evaluate it, and...

Id say a pipeline thats loosely: ` audio