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

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.

yoavg

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

daniestevez

<?xml version='1.0' encoding='utf-8'?>
<?grc format='1' created='3.7.13'?>
<flow_graph>
  <timestamp>Tue Apr  2 21:50:17 2019</timestamp>
  <block>
    <key>options</key>
    <param>
      <key>author</key>
      <value></value>
    </param>

HarshSingh16

########loading the Titanic Train Data Set
TitanicTrain<-train1

######Checking Missing Values in the Train Data Set
sapply(TitanicTrain, function(x)sum(is.na(x)))

#######Loading the Titanic Test Data Set
TitanicTest<-test11

#######Checking Missing Values in the Test Data Set

knbknb

# see also:
# https://s3.amazonaws.com/assets.datacamp.com/blog_assets/xts_Cheat_Sheet_R.pdf


# Open csv file using read.zoo
my_tsdata <- read.zoo("my_tsdata.csv", sep = ",", FUN = as.Date, header = TRUE, index.column = 1)
my_tsdata <- as.xts(my_tsdata)


 

terabyte

Prologue

I wrote this answer on stackexchange, here: https://stackoverflow.com/posts/12597919/

It was wrongly deleted for containing "proprietary information" years later. I think that's bullshit so I am posting it here. Come at me.

The Question

Amazon is a SOA system with 100s of services (or so says Amazon Chief Technology Officer Werner Vogels). How do they handle build and release?

5agado

max-mapper

{"help": "https://catalog.data.gov/api/3/action/help_show?name=package_search", "success": true, "result": {"count": 48, "sort": "views_recent desc", "facets": {}, "results": [{"license_title": "License not specified", "maintainer": "New Media", "relationships_as_object": [], "private": false, "maintainer_email": "[email protected]", "num_tags": 5, "id": "59694770-b6b6-4ae0-a4b9-4ae69c0be2f6", "metadata_created": "2016-07-02T10:06:26.199575", "metadata_modified": "2016-07-02T10:06:26.199575", "author": null, "author_email": null, "state": "active", "version": null, "creator_user_id": "47303a9e-1187-4290-85a3-1fc02dc49e4a", "type": "dataset", "resources": [{"cache_last_updated": null, "package_id": "59694770-b6b6-4ae0-a4b9-4ae69c0be2f6", "webstore_last_updated": null, "id": "3a8a0ad1-19e7-4153-bb2f-d70cf88aaaf8", "size": null, "state": "active", "hash": "", "description": "", "format": "CSV", "tracking_summary": {"total": 32, "recent": 1}, "last_modified": null, "url_type": null, "no_real_name": "True", 

tgh0831

##### This is a simple RODBC example
##### The ODBCDriverName will be the driver name in ODBC Administrator

require(RODBC)

#open the ODBC connection
ch <- odbcConnect("ODBCDriverName")

##### Alternative ODBC connection for Microsoft SQL Server
ch <- odbcDriverConnect(