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

schacon

require 'rugged'

# Your specified file is the first argument
file_path = ARGV[0]

repo = Rugged::Repository.discover(File.dirname(file_path))
walker = Rugged::Walker.new(repo)
walker.push(repo.head.target.oid)
walker.sorting(Rugged::SORT_TOPO)

stufro

# spec.cr
require "spectator"
require "./spec_helper"

Spectator.describe OrderCalculator do
  inject_mock Database
  def_mock(Product)

  it "multiplies the product price by given quantity" do
    product = new_mock(Product)

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.

kddnewton

# frozen_string_literal: true

require "bundler/inline"

gemfile do
  source "https://rubygems.org"
  gem "json_pure"
  gem "benchmark-ips"
end

jonathantneal

interface Iterator<T, TReturn = any, TNext = undefined> {
	next(): {
		done: boolean
		value: T
	}

	/** Returns an iterator of the elements with the given mapping function applied. */
	map<TT>(
		/** A mapping function to call on every element of the iterator. */
		callback: (value: T) => TT

codepo8

var tryCount = 0;
var minimalUserResponseInMiliseconds = 200;
function check() {
  console.clear();
  before = new Date().getTime();
  debugger;
  after = new Date().getTime();
  if (after - before > minimalUserResponseInMiliseconds) {
    document.write(" Dont open Developer Tools. ");
    self.location.replace(window.location.protocol + window.location.href.substring(window.location.protocol.length));

timohuovinen

Virtualbox (free and open-source)

How to install an unlicensed copy of windows using virtualbox

1. Install virtualbox 7 (or higher)
   1. Ubuntu 22.04 jammy for linux mint 21
   2. Download extensions pack for the same version.
2. Virtualbox > Tools > Install Oracle VM Virtualbox Extensions Pack for the same version
3. Download Windows 10 pro from Microsoft
4. Create a machine
   1. System > Motherboard > Check EFI and Secure boot (boot order won’t work with EFI, required for windows 11)
5. System > Motherboard > Check TPM 2.0 (Security chip emulation)

MarioRuiz

# Requires an Apple Mac and Ruby
# I created this gist just to help my daughter to learn how words are written in Spanish and English.
# The script will pronounce a random word in the language selected and the child needs to write the word letter by letter.

require 'string_pattern'
require 'open3'
require 'io/console'

ENV['NOMBRE'] ||= 'Pedro'
ENGLISH = ENV['ENGLISH'] == 'true'

dxdxdt

What to do when Gmail marks all the mails from your server as spam

If you're self-hosting your services and having trouble getting your emails through Gmail and infuriated by Google's non-existent support, you're not the only one. I'd like to share my experiences trying to get it sorted out.

• https://support.google.com/mail/thread/171517615?hl=en&msgid=172576102

I'm the author of the post above. You can tell how arrogant Google employees are from all the previous posts he made in the past.