You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
GGML_OPENCL_DEVICE=1 nix run 'github:ggerganov/llama.cpp#opencl' -- -m models/52468fe965d4fd1c4f7c596665ef5bac2f290f413591bd35cd619143b201375c -p"Building a website can be done in 10 simple steps:"-n 512 --n-gpu-layers 1
If this helps, I have a 1650 ti.
Edit: It seems to work fine on my non-nixos (debian) machine with a 6600 xt and double the vram (8gb).
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
GGML seems to crash after spamming that it can't find inp0.
I used the following command to run the model I downloaded from https://huggingface.co/NikolayKozloff/falcon-7b-GGUF/tree/main.
If this helps, I have a 1650 ti.
Edit: It seems to work fine on my non-nixos (debian) machine with a 6600 xt and double the vram (8gb).
Beta Was this translation helpful? Give feedback.
All reactions