Filter | Description | Example |
---|---|---|
allintext | Searches for occurrences of all the keywords given. | allintext:"keyword" |
intext | Searches for the occurrences of keywords all at once or one at a time. | intext:"keyword" |
inurl | Searches for a URL matching one of the keywords. | inurl:"keyword" |
allinurl | Searches for a URL matching all the keywords in the query. | allinurl:"keyword" |
intitle | Searches for occurrences of keywords in title all or one. | intitle:"keyword" |
echo "If your SSH key has a passphrase, you might need to enter it each time. Consider using ssh-agent or removing the passphrase"; | |
while read p; do | |
echo "$p"; | |
git clone "$p"; | |
done < $1 |
A curated list of arrrrrrrrr!
This gist is a note about install nvidia-docker
in Pop!_OS 20.10
. nvidia-docker
is used to help docker containers compute on GPU.
The basic installcation is in Nvidia's offical documentation. But there are a few tweaks to make it work on Pop!_OS 20.10
.
No surprise. Follow the offical documentaion should work.
tl;dr use Linux, install bitsandbytes
(either globally or in KAI's conda env, add load_in_8bit=True
, device_map="auto"
in model pipeline creation calls)
Many people are unable to load models due to their GPU's limited VRAM. These models contain billions of parameters (model weights and biases), each of which is a 32 (or 16) bit float. Thanks to the hard work of some researchers [1], it's possible to run these models using 8-bit numbers, which halves the required amount of VRAM compared to running in half-precision. E.g. if a model requires 16GB of VRAM, running with 8-bit inference only requires 8GB.
This guide was written for KoboldAI 1.19.1, and tested with Ubuntu 20.04. These instructions are based on work by Gmin
in KoboldAI's Discord server, and Huggingface's efficient LM inference guide.