RichardoC

joined 1 year ago
 

Anyone had any luck fine tuning Llama3.1 using a macbook and written a recent guide?

I've got some conversations I saved from interacting with Llama and have tweaked to be what I actually wanted and was wondering how best to go about fine tuning the model to see if this data makes it better at my use case (converting cloud formation to openTofu)

Thanks!

 

"Apparently if 1985 by Bowling For Soup were released today, it would be about 2005. Anyways, here's what that would probably sound like. " - from their description because I couldn't phrase it better myself

[–] RichardoC@lemmy.world 55 points 2 months ago (1 children)

Nothing, it's already ruined(!)

[–] RichardoC@lemmy.world 4 points 3 months ago
 
 

Currently discussing this with my Bulgarian partner, apparently this is a normal breakfast in tomato Europe, either with or without feta cheese. I'm from potato Europe and have never heard of this madness!

[–] RichardoC@lemmy.world 1 points 4 months ago

Jan.ai might be a good starting point or ollama? There's https://tales.fromprod.com/2024/111/using-your-own-hardware-for-llms.html which has some guidance for using jan.ai for both server and client

[–] RichardoC@lemmy.world 13 points 5 months ago (3 children)

Is that image AI generated? There are a different number of columns at the top compared to the bottom

[–] RichardoC@lemmy.world 17 points 5 months ago

You're looking for something to export the image at a lower resolution (resize) rather than something to compress the image. Any open source gallery/image editing app should be able to do this.

One example would be "image toolbox" on FDroid. I've not used it but it seems to have the feature you need

[–] RichardoC@lemmy.world 7 points 8 months ago (1 children)

It's a Stargate SG1 reference

[–] RichardoC@lemmy.world 14 points 8 months ago (2 children)

What "language" is this?

[–] RichardoC@lemmy.world 68 points 9 months ago (13 children)

Would someone mind explaining this for a non-american?