veekaybee

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

rain-1

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.

nopeless

// Prime checking regex, which this code is based off of
// https://regex101.com/r/RIJkGF/1

type StringDivisible<n extends string, div extends string> = n extends `` ? true : n extends `${div}${infer r}` ? StringDivisible<r, div> : false;

type Substrings<n extends string, d extends string = ""> = n extends `${d}${infer r}` ? readonly [` ${d}`, ...Substrings<r, ` ${d}`>] : readonly [];
type StringFactors<n extends string> = Substrings<n> extends readonly [unknown, ...infer R extends readonly string[], unknown] ? R : never;
type StringIsPrime<n extends string, Factors extends readonly string[] = StringFactors<n>> = Factors extends readonly [infer s extends string, ...infer R extends readonly string[]] ? StringDivisible<n, s> extends true ? false : StringIsPrime<n, R> : true;

type RepeatStringByStringDigit<str extends string, d extends string> = 

bitti

#!/usr/bin/ruby
require 'redcarpet'
require 'erb'

input = ARGV[0] && ARGV[0] != "-" &&  File.open(ARGV[0]) || STDIN
output = ARGV[1] && File.open(ARGV[1], "w") || STDOUT

File.join(ENV["XDG_CACHE_HOME"] || "#{ENV['HOME']}/.cache", "gfm-render")

class RenderWithTaskLists < Redcarpet::Render::HTML

travisbrown

Amir22010

Convert PascalVOC Annotations to YOLO

This script reads PascalVOC xml files, and converts them to YOLO txt files.

Note: This script was written and tested on Ubuntu. YMMV on other OS's.

Disclaimer: This code is a modified version of Joseph Redmon's voc_label.py

Instructions:

1. Place the convert_voc_to_yolo.py file into your data folder.

antirez

# LVDB - LLOOGG Memory DB
# Copyriht (C) 2009 Salvatore Sanfilippo <antirez@gmail.com>
# All Rights Reserved

# TODO
# - cron with cleanup of timedout clients, automatic dump
# - the dump should use array startsearch to write it line by line
#   and may just use gets to read element by element and load the whole state.
# - 'help','stopserver','saveandstopserver','save','load','reset','keys' commands.
# - ttl with milliseconds resolution 'ttl a 1000'. Check ttl in dump!

dimkir

Running nightmare on Amazon Linux

You may have thought of running nightmare on AWS Lambda. But before we can run it on Lambda, we need first to make it run on Amazon Linux.

Provision instance which replicates Lambda environment

According to AWS Documentation on Lambda Execution Environment and available Libraries we would need this AMI image with this alias amzn-ami-hvm-2016.03.3.x86_64-gp2. Keep in mind that AMI-image-id for this instance would be different in different regions (eg):

• In eu-west-1 - ami-f9dd458a
• In us-east-1 - ami-6869aa05

kaspergrubbe

# VTE
apt-get install autoconf libglib2.0-dev gtk-doc-tools libpcre2-dev libgirepository1.0-dev gperf libvte-2.91-dev libvte-dev valac unzip
wget https://github.com/thestinger/vte-ng/archive/0.46.0.a.zip
unzip 0.46.0.a.zip
rm 0.46.0.a.zip
cd vte-ng-0.46.0.a
bash autogen.sh
make && make install
cd ~
rm -rf vte-ng-0.46.0.a/

rondy

FWIW: I (@rondy) am not the creator of the content shared here, which is an excerpt from Edmond Lau's book. I simply copied and pasted it from another location and saved it as a personal note, before it gained popularity on news.ycombinator.com. Unfortunately, I cannot recall the exact origin of the original source, nor was I able to find the author's name, so I am can't provide the appropriate credits.

---

Effective Engineer - Notes

• By Edmond Lau
• Highly Recommended 👍
• http://www.theeffectiveengineer.com/

What's an Effective Engineer?