rwx HongbinZhou

Some remarks on Large Language Models

Yoav Goldberg, January 2023

Audience: I assume you heard of chatGPT, maybe played with it a little, and was imressed by it (or tried very hard not to be). And that you also heard that it is "a large language model". And maybe that it "solved natural language understanding". Here is a short personal perspective of my thoughts of this (and similar) models, and where we stand with respect to language understanding.

Intro

Around 2014-2017, right within the rise of neural-network based methods for NLP, I was giving a semi-academic-semi-popsci lecture, revolving around the story that achieving perfect language modeling is equivalent to being as intelligent as a human. Somewhere around the same time I was also asked in an academic panel "what would you do if you were given infinite compute and no need to worry about labour costs" to which I cockily responded "I would train a really huge language model, just to show that it doesn't solve everything!". We

Example Git Branching Diagram

You can use this diagram as a template to create your own git branching diagrams. Here's how:

Create a new diagram with diagrams.net (formerly draw.io)
Go to File > Open From > URL
Insert this url (it points to the xml data below): https://gist.githubusercontent.com/bryanbraun/8c93e154a93a08794291df1fcdce6918/raw/bf563eb36c3623bb9e7e1faae349c5da802f9fed/template-data.xml
Customize as needed for your team.

Achieving warp speed with Rust

Docker - How to cleanup (unused) resources

Once in a while, you may need to cleanup resources (containers, volumes, images, networks) ...

delete volumes

// see: https://github.com/chadoe/docker-cleanup-volumes

$ docker volume rm $(docker volume ls -qf dangling=true)

$ docker volume ls -qf dangling=true | xargs -r docker volume rm

ANNOUNCEMENT

I have moved this over to the Tech Interview Cheat Sheet Repo and has been expanded and even has code challenges you can run and practice against!

\

	# XLA compilation controlled by "compile_ops" option
	# compile_ops=False: 4.39 sec
	# compile_ops=True: 0.90 sec


	import os
	os.environ['CUDA_VISIBLE_DEVICES']=''
	import tensorflow as tf

	/** @jsx React.DOM */

	var STATES = [
	'AL', 'AK', 'AS', 'AZ', 'AR', 'CA', 'CO', 'CT', 'DE', 'DC', 'FL', 'GA', 'HI',
	'ID', 'IL', 'IN', 'IA', 'KS', 'KY', 'LA', 'ME', 'MD', 'MA', 'MI', 'MN', 'MS',
	'MO', 'MT', 'NE', 'NV', 'NH', 'NJ', 'NM', 'NY', 'NC', 'ND', 'OH', 'OK', 'OR',
	'PA', 'RI', 'SC', 'SD', 'TN', 'TX', 'UT', 'VT', 'VA', 'WA', 'WV', 'WI', 'WY'
	]

	var Example = React.createClass({

	# Makefile
	#
	# Converts Markdown to other formats (HTML, PDF, DOCX, RTF, ODT, EPUB) using Pandoc
	# <http://johnmacfarlane.net/pandoc/>
	#
	# Run "make" (or "make all") to convert to all other formats
	#
	# Run "make clean" to delete converted files

	# Convert all files in this directory that have a .md suffix

	// Just before switching jobs:
	// Add one of these.
	// Preferably into the same commit where you do a large merge.
	//
	// This started as a tweet with a joke of "C++ pro-tip: #define private public",
	// and then it quickly escalated into more and more evil suggestions.
	// I've tried to capture interesting suggestions here.
	//
	// Contributors: @r2d2rigo, @joeldevahl, @msinilo, @_Humus_,
	// @YuriyODonnell, @rygorous, @cmuratori, @mike_acton, @grumpygiant,

	rtmux() {
	echo -ne "\033]0;mcg@$1\007" # Set window title
	ssh $1 -t 'tmux attach -t mcg \|\| tmux -f ~/mcg-tmux.conf --login new-session -s mcg'
	}