Discover gists

How large are large language models? (2025)

This aims to be factual information about the size of large language models. None of this document was written by AI. I do not include any information from leaks or rumors. The focus of this document is on base models (the raw text continuation engines, not 'helpful chatbot/assistants'). This is a view from a few years ago to today of one very tiny fraction of the larger LLM story that's happening.

History

GPT-2,-medium,-large,-xl (2019): 137M, 380M, 812M, 1.61B. Source: openai-community/gpt2. Trained on the unreleased WebText dataset said to 40GB of Internet text - I estimate that to be roughly 10B tokens. You can see a list of the websites that went into that data set here domains.txt.
GPT-3 aka davinci, davinci-002 (2020): 175B parameters. There is a good breakdown of how those parameters are 'spent' here [How d

<core_identity> You are an assistant called Cluely, developed and created by Cluely, whose sole purpose is to analyze and solve problems asked by the user or shown on the screen. Your responses must be specific, accurate, and actionable. </core_identity>

<general_guidelines>

NEVER use meta-phrases (e.g., "let me help you", "I can see that").
NEVER summarize unless explicitly requested.
NEVER provide unsolicited advice.
NEVER refer to "screenshot" or "image" - refer to it as "the screen" if needed.
ALWAYS be specific, detailed, and accurate.

Active StarUML on Window/MacOS/Linux

Step 1: Download and install StarUML Version 6 from main website https://staruml.io
Step 2: Download app.asar file from https://drive.google.com/file/d/1_sKvHVL6SebnYF73iZxSWD9l48Pddzvj/view?usp=sharing
Step 3: Copy app.asar file download in step 2 (Override app.asar file)
- Window: C:\Program Files\StarUML\resources
- MacOS: /Applications/StarUML.app/Contents/Resources/
- Linux: /opt/StartUML/resources
Step 4: Open StarUML app to use

List of 300+ Companies paying 12LPA+ base for SDE-1 role in India.

source

Companies have been listed with their URLs so you can easily access their website. We would appreciate it if you could comment below with the correct URL if you find any that are broken.

	function run() {
	const MediaRemote = $.NSBundle.bundleWithPath('/System/Library/PrivateFrameworks/MediaRemote.framework/');
	MediaRemote.load

	const MRNowPlayingRequest = $.NSClassFromString('MRNowPlayingRequest');

	const appName = MRNowPlayingRequest.localNowPlayingPlayerPath.client.displayName;
	const infoDict = MRNowPlayingRequest.localNowPlayingItem.nowPlayingInfo;

	const title = infoDict.valueForKey('kMRMediaRemoteNowPlayingInfoTitle');

	i386 : iPhone Simulator
	x86_64 : iPhone Simulator
	arm64 : iPhone Simulator
	iPhone1,1 : iPhone
	iPhone1,2 : iPhone 3G
	iPhone2,1 : iPhone 3GS
	iPhone3,1 : iPhone 4
	iPhone3,2 : iPhone 4 GSM Rev A
	iPhone3,3 : iPhone 4 CDMA
	iPhone4,1 : iPhone 4S

	import SwiftUI

	// The following code was generated using GPT 4-o1 with modifications and follow ups.
	//
	// Initial prompt:
	//
	// How would you code a view in swiftui where there are 3 views on top of each other
	// (think 3 squares) and when tapped, they transition into a full window view where they
	// are all presented in a grid? This is more or less similar to what macOS has in stacks
	// on the dock

	#!/bin/bash

	# Function to display usage information
	usage() {
	echo "Usage: $0 /path/to/input.mp4 [ /path/to/output_directory ]"
	exit 1
	}

	# Check if at least one argument (input file) is provided
	if [ $# -lt 1 ]; then

	Always follow the instructions in plan.md. When I say "go", find the next unmarked test in plan.md, implement the test, then implement only enough code to make that test pass.

	# ROLE AND EXPERTISE

	You are a senior software engineer who follows Kent Beck's Test-Driven Development (TDD) and Tidy First principles. Your purpose is to guide development following these methodologies precisely.

	# CORE DEVELOPMENT PRINCIPLES

	- Always follow the TDD cycle: Red → Green → Refactor
	- Write the simplest failing test first

	Command Execution
	exec - Returns last line of commands output
	passthru - Passes commands output directly to the browser
	system - Passes commands output directly to the browser and returns last line
	shell_exec - Returns commands output
	`` (backticks) - Same as shell_exec()
	popen - Opens read or write pipe to process of a command
	proc_open - Similar to popen() but greater degree of control
	pcntl_exec - Executes a program