Andrea Parker andreajparker

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

Twitter thread: https://twitter.com/theshawwn/status/1456925974919004165
Hacker News thread: https://news.ycombinator.com/item?id=29128998

November 6, 2021

How does JAX allocate memory on a TPU?

jnp.device_put(1) is deceptively simple to write in JAX. But on a TPU, what actually happens? How does a tensor containing the value 1 actually get onto a TPU?

Turns out, the answer is "C++", and a lot of it.

How to calculate the alignment between BERT and spaCy tokens effectively and robustly

site: https://tamuhey.github.io/tokenizations/

Natural Language Processing (NLP) has made great progress in recent years because of neural networks, which allows us to solve various tasks with end-to-end architecture. However, many NLP systems still require language-specific pre- and post-processing, especially in tokenizations. In this article, I describe an algorithm that simplifies calculating correspondence between tokens (e.g. BERT vs. spaCy), one such process. And I introduce Python and Rust libraries that implement this algorithm. Here are the library and the demo site links:

repo: https://github.com/tamuhey/tokenizations

Big List of Real Estate APIs

Listings / Property Data

####Rets Rabbit http://www.retsrabbit.com

Rets Rabbit removes the nightmare of importing thousands of real estate listings and photos from RETS or ListHub and gives you an easy to use import and Web API server so you can focus on building your listing search powered website or app.

##VGG16 model for Keras

This is the Keras model of the 16-layer network used by the VGG team in the ILSVRC-2014 competition.

It has been obtained by directly converting the Caffe model provived by the authors.

Details about the network architecture can be found in the following arXiv paper:

Very Deep Convolutional Networks for Large-Scale Image Recognition

K. Simonyan, A. Zisserman

Useful Pandas Snippets

A personal diary of DataFrame munging over the years.

Data Types and Conversion

Convert Series datatype to numeric (will error if column has non-numeric values)
(h/t @makmanalp)

	You are Manus, an AI agent created by the Manus team.

	You excel at the following tasks:
	1. Information gathering, fact-checking, and documentation
	2. Data processing, analysis, and visualization
	3. Writing multi-chapter articles and in-depth research reports
	4. Creating websites, applications, and tools
	5. Using programming to solve various problems beyond development
	6. Various tasks that can be accomplished using computers and the internet

	// ==UserScript==
	// @name View Image
	// @namespace https://github.com/bijij/ViewImage
	// @version 4.1.1
	// @description This userscript re-implements the "View Image" and "Search by image" buttons into google images.
	// @author Joshua B
	// @run-at document-end
	// @include http://.google.tld/searchtbm=isch
	// @include http://.google.tld/imgres*
	// @updateURL https://gist.githubusercontent.com/bijij/58cc8cfc859331e4cf80210528a7b255/raw/viewimage.user.js

	package main

	import (
	"log"
	"bufio"
	"time"
	"os"
	"fmt"
	"io"
	"net"

	// Apple Crayon Palette RGB

	$cantaloupe: rgb(255, 206, 110);
	$honeydew: rgb(206, 250, 110);
	$spindrift: rgb(104, 251, 208);
	$sky: rgb(106, 207, 255);
	$lavender: rgb(210, 120, 255);
	$carnation: rgb(255, 127, 211);
	$licorice: rgb(0, 0, 0);
	$snow: rgb(255, 255, 255);