[Linux-aus] Flounder meeting Nov 10th LLM/AI

[Russell Coker]

https://flounder.linux.org.au/events/flounder-oct-2024-llm-hack/

November event LLM hack day. Russell will talk about AI/LLMs and provide 
access to a server running CUDA with some LLMs installed. Hands on experience 
using an NVidia GPU for LLM.

Meeting will be at http://b.coker.com.au. No need to register just click on 
the link on the day.

Meeting officially opens at 1PM Melbourne time (02:00UTC), 10th of November.

Some useful URLs:

https://huggingface.co/microsoft/phi-2 – Microsoft Phi-2 LLM – needs almost 
12G of GPU RAM.
https://github.com/ggerganov/llama.cpp – Running the Llama model via a C++ 
program.
https://boinc.berkeley.edu/wiki/GPU_computing – how to donate your GPU power 
to research projects via BIONC.


This meeting is on a Sunday because the consensus of opinion in the Matrix 
room was that Sunday is better than Saturday for this weekend.

Also if someone is good at Python and would like to join that would be really 
good.  So far I've been writing the Python I need for this sort of thing by 
just Googling it.  Maybe I should switch to using a LLM. ;)

-- 
My Main Blog         http://etbe.coker.com.au/
My Documents Blog    http://doc.coker.com.au/