Belluxx
Belluxx
Had the same problem on the Raspberry Pi 4 and i solved it: `sudo echo "blacklist hp_wmi" > /etc/modprobe.d/hp.conf` `sudo reboot` `sudo rfkill unblock all` Credit: https://bbs.archlinux.org/viewtopic.php?pid=1324810#p1324810
@astroboylrx I am facing the same issue, did you find a solution? I also opened an issue about it #4607
> Try using the iso from uupdump instead of from microsoft.com . I tried both and experienced the same issue
I confirm that the issue is still there in v0.123.4
@effdotsh Thank you for providing a fix so quickly
@BadisG Yeah i agree that's an issue, however LLaMA misuses that flag in conversations that have nothing to do with code and after printing the flag it starts outputting nonsense....
@PriNova so you didn't have the issue before #252? Have you tried using the older version of the repo to see if the issue disappears?
That's amazing thanks @rabidcopy, i will test it asap. Another issue that i noticed is that sometimes LLaMA stops mid generation and you need to press enter to make it...
> maybe you are lucky with this one? https://huggingface.co/ozcur/alpaca-native-4bit/tree/main maybe this was generated just before the zeros patch was merged. Just tried, it fails with `KeyError: 'model.layers.0.self_attn.q_proj.zeros'`
@BadisG Did you notice an increase in model size after converting to ggml? The 7B one i converted went from 3.77GB to 5.39GB and inference is significantly slower, but it...