Skip to content

Instantly share code, notes, and snippets.

@rain-1
rain-1 / llama-home.md
Last active December 30, 2024 14:09
How to run Llama 13B with a 6GB graphics card

This worked on 14/May/23. The instructions will probably require updating in the future.

llama is a text prediction model similar to GPT-2, and the version of GPT-3 that has not been fine tuned yet. It is also possible to run fine tuned versions (like alpaca or vicuna with this. I think. Those versions are more focused on answering questions)

Note: I have been told that this does not support multiple GPUs. It can only use a single GPU.

It is possible to run LLama 13B with a 6GB graphics card now! (e.g. a RTX 2060). Thanks to the amazing work involved in llama.cpp. The latest change is CUDA/cuBLAS which allows you pick an arbitrary number of the transformer layers to be run on the GPU. This is perfect for low VRAM.

  • Clone llama.cpp from git, I am on commit 08737ef720f0510c7ec2aa84d7f70c691073c35d.
@Lukas-Krickl
Lukas-Krickl / 00-project-reactor-from-zero-to-hero.md
Last active January 14, 2025 18:29
A java project reactor tutorial/discussion reaching from basic concepts to reactor internal implementation details.

Project Reactor: From Zero to Hero

In this series of pages, I will discuss project reactor and reactive programming from basic concepts to reactor internal implementation details. This discussion is based on the official reference documentation, the java-doc, talks by maintainers of reactor e.g. at the spring I/O and other distributed material, and should summarise and connect all this information. It should complement the official reference documentation and java-doc. Although the name says "from zero to hero", basic knowledge about the library is advised to fully benefit from it.

As a short disclaimer, I am a professional software engineer with some years of experience in using reactor, but not a maintainer or creator of the library. Information and knowledge in this post are based on the official documentation and talks, but I cannot exclude misconceptions on my side.


  1. [Why and when to use Reactor](https://gist.github.com/Lukas-Krickl/50f1daebebaa72c7e944b7c319e3c073#file-01-why-and-when-to-use
@rain-1
rain-1 / LLM.md
Last active January 8, 2025 13:30
LLM Introduction: Learn Language Models

Purpose

Bootstrap knowledge of LLMs ASAP. With a bias/focus to GPT.

Avoid being a link dump. Try to provide only valuable well tuned information.

Prelude

Neural network links before starting with transformers.

@eviltester
eviltester / gist:11093f0e4c501a41990e227393184eda
Last active December 22, 2024 08:02
uncheck twitter interests
var timer=100;document.querySelectorAll("div > input[type='checkbox']:checked").forEach((interest) => {setTimeout(function(){interest.click()},timer);timer+=2000;});
@alanbuxey
alanbuxey / stubby.xml
Last active December 13, 2024 09:22
Cloudflare Stubby config
#
# This is a yaml version of the stubby configuration file (it replaces the
# json based stubby.conf file used in earlier versions of getdns/stubby).
#
# For more information see
# https://dnsprivacy.org/wiki/display/DP/Configuring+Stubby
#
# This format does not fully support all yaml features - the restrictions are:
# - the outer-most data structure must be a yaml mapping
# - mapping keys must be yaml scalars
http://www.oreilly.com/data/free/files/2014-data-science-salary-survey.pdf
http://www.oreilly.com/data/free/files/2015-data-science-salary-survey.pdf
http://www.oreilly.com/data/free/files/Data_Analytics_in_Sports.pdf
http://www.oreilly.com/data/free/files/advancing-procurement-analytics.pdf
http://www.oreilly.com/data/free/files/ai-and-medicine.pdf
http://www.oreilly.com/data/free/files/analyzing-data-in-the-internet-of-things.pdf
http://www.oreilly.com/data/free/files/analyzing-the-analyzers.pdf
http://www.oreilly.com/data/free/files/architecting-data-lakes.pdf
http://www.oreilly.com/data/free/files/being-a-data-skeptic.pdf
http://www.oreilly.com/data/free/files/big-data-analytics-emerging-architecture.pdf
@CristinaSolana
CristinaSolana / gist:1885435
Created February 22, 2012 14:56
Keeping a fork up to date

1. Clone your fork:

git clone [email protected]:YOUR-USERNAME/YOUR-FORKED-REPO.git

2. Add remote from original repository in your forked repository:

cd into/cloned/fork-repo
git remote add upstream git://github.com/ORIGINAL-DEV-USERNAME/REPO-YOU-FORKED-FROM.git
git fetch upstream