Matt Olander
Matt Olander
same
+1! We can start by just honoring anything with: OPENAI_API_BASE= or perhaps passing the proxy option could work: OPENAI_API_PROXY= Great project btw! Kudos and thank you for open-sourcing! Since it...
Ah, gotcha! I was almost there but I didn't put the --path arg on the ./server running outside of /baby-code dir, so I got confused when the standard llama.cpp page...
haha, maybe. I have it but it is just not as fun for some reason. there is no confetti! ;)
Sorry, missed that one! That is fantastic!! Haha, this is still my fav and I use him to help with a lot of sysadmin tasks from my FreeBSD box. Ummm...
RuntimeError: Error: More than 1 GPUs have a lot of VRAM usage. Please obtain a commercial license. Thanks for all your work, btw! Killer project! ==((====))== Unsloth - 2x faster...
Can confirm it does not occur with unsloth-2024.5 but does at unsloth-2024.6 If necessary, one can downgrade via: pip install --upgrade --force-reinstall --no-cache-dir git+https://github.com/unslothai/unsloth.git@f9689b1
@danielhanchen no, as soon as I uninstall and pip install --upgrade --force-reinstall --no-cache-dir git+https://github.com/unslothai/unsloth.git, it comes back :(
Confirmed not working as intended. Nothing going on GPU = 1, will not run, even though Num GPUs shows as 1 in Unsloth banner below. But on GPU = 0,...
@danielhanchen Good to go here! I made a new conda env and conda installed pytorch, transformers, etc and it's working like a mule at the grand canyon! Thanks!