Large Language Models On Small Computers

September 7, 2024 by Bryan Cockfield 6 Comments

As technology progresses, we generally expect processing capabilities to scale up. Every year, we get more processor power, faster speeds, greater memory, and lower cost. However, we can also use improvements in software to get things running on what might otherwise be considered inadequate hardware. Taking this to the extreme, while large language models (LLMs) like GPT are running out of data to train on and having difficulty scaling up, [DaveBben] is experimenting with scaling down instead, running an LLM on the smallest computer that could reasonably run one.

Of course, some concessions have to be made to get an LLM running on underpowered hardware. In this case, the computer of choice is an ESP32, so the dataset was reduced from the trillions of parameters of something like GPT-4 or even hundreds of billions for GPT-3 down to only 260,000. The dataset comes from the tinyllamas checkpoint, and llama.2c is the implementation that [DaveBben] chose for this setup, as it can be streamlined to run a bit better on something like the ESP32. The specific model is the ESP32-S3FH4R2, which was chosen for its large amount of RAM compared to other versions since even this small model needs a minimum of 1 MB to run. It also has two cores, which will both work as hard as possible under (relatively) heavy loads like these, and the clock speed of the CPU can be maxed out at around 240 MHz.

Admittedly, [DaveBben] is mostly doing this just to see if it can be done since even the most powerful of ESP32 processors won’t be able to do much useful work with a large language model. It does turn out to be possible, though, and somewhat impressive, considering the ESP32 has about as much processing capability as a 486 or maybe an early Pentium chip, to put things in perspective. If you’re willing to devote a few more resources to an LLM, though, you can self-host it and use it in much the same way as an online model such as ChatGPT.

Hackaday Links: September 1, 2024

September 1, 2024 by Dan Maloney 21 Comments

Why is it always a helium leak? It seems whenever there’s a scrubbed launch or a narrowly averted disaster, space exploration just can’t get past the problems of helium plumbing. We’ve had a bunch of helium problems lately, most famously with the leaks in Starliner’s thruster system that have prevented astronauts Butch Wilmore and Suni Williams from returning to Earth in the spacecraft, leaving them on an extended mission to the ISS. Ironically, the launch itself was troubled by a helium leak before the rocket ever left the ground. More recently, the Polaris Dawn mission, which is supposed to feature the first spacewalk by a private crew, was scrubbed by SpaceX due to a helium leak on the launch tower. And to round out the helium woes, we now have news that the Peregrine mission, which was supposed to carry the first commercial lander to the lunar surface but instead ended up burning up in the atmosphere and crashing into the Pacific, failed due to — you guessed it — a helium leak.
Continue reading “Hackaday Links: September 1, 2024” →

Peering Into The Black Box Of Large Language Models

July 3, 2024 by Donald Papp 34 Comments

Large Language Models (LLMs) can produce extremely human-like communication, but their inner workings are something of a mystery. Not a mystery in the sense that we don’t know how an LLM works, but a mystery in the sense that the exact process of turning a particular input into a particular output is something of a black box.

This “black box” trait is common to neural networks in general, and LLMs are very deep neural networks. It is not really possible to explain precisely why a specific input produces a particular output, and not something else.

Why? Because neural networks are neither databases, nor lookup tables. In a neural network, discrete activation of neurons cannot be meaningfully mapped to specific concepts or words. The connections are complex, numerous, and multidimensional to the point that trying to tease out their relationships in any straightforward way simply does not make sense.

Continue reading “Peering Into The Black Box Of Large Language Models” →

Torment Poor Milton With Your Best Pixel Art

June 25, 2024 by Donald Papp 7 Comments

One of the great things about new tech tools is just having fun with them, like embracing your inner trickster god to mess with ‘Milton’, an AI trapped in an empty room.

Milton is trapped in a room is a pixel-art game with a simple premise: use a basic paint interface to add objects to the room, then watch and listen to Milton respond to them. That’s it? That’s it. The code is available on the GitHub repository, but there’s also a link to play it live without any kind of signup or anything. Give it a try if you have a few spare minutes.

Under the hood, the basic loop is to let the user add something to the room, send the picture of the room (with its new contents) off for image recognition, then get Milton’s reaction to it. Milton is equal parts annoyed and jumpy, and his speech and reactions reflect this.

The game is a bit of a concept demo for Open Souls whose “thing” is providing AIs with far more personality and relatable behaviors than one typically expects from large language models. Maybe this is just what’s needed for AI opponents in things like the putting game of Connect Fore! to level up their trash talking.

NetBSD Bans AI-Generated Code From Commits

May 18, 2024 by Maya Posch 38 Comments

A recent change was announced to the NetBSD commit guidelines which amends these to state that code which was generated by Large Language Models (LLMs) or similar technologies, such as ChatGPT, Microsoft’s Copilot or Meta’s Code Llama is presumed to be tainted code. This amendment was to the existing section about tainted code, which originally referred to any code that was not written directly by the person committing the code, and was due to licensing concerns. The obvious reason behind this is that otherwise code may be copied into the NetBSD codebase which may have been licensed under an incompatible (or proprietary) license.

In the case of LLM-based code generators like the above-mentioned, the problem stems from the fact that they are trained on millions of lines of code from all over the internet, which are naturally released under a wide variety of licenses. Invariably, some of that code will be covered by a license that’s not acceptable for the NetBSD codebase. Although the guideline mentions that these auto-generated code commits may still be admissible, they require written permission from core developers, and presumably an in-depth audit of the code’s heritage. This should leave non-trivial commits that got churned out by ChatGPT and kin out in the cold.

The debate about the validity of works produced by current-gen “artificial intelligence” software is only just beginning, but there’s little question that NetBSD has made the right call here. From a legal and software engineering perspective this policy makes perfect sense, as LLM-generated code simply doesn’t meet the project’s standards. That said, code produced by humans brings with it a whole different set of potential problems.

How AI Large Language Models Work, Explained Without Math

May 15, 2024 by Donald Papp 24 Comments

Large Language Models (LLMs ) are everywhere, but how exactly do they work under the hood? [Miguel Grinberg] provides a great explanation of the inner workings of LLMs in simple (but not simplistic) terms that eschews the low-level mathematics of how they work in favor of laying bare what it is they do.

At their heart, LLMs are prediction machines that work on tokens (small groups of letters and punctuation) and are as a result capable of great feats of human-seeming communication. Most technical-minded people understand that LLMs have no idea what they are saying, and this peek at their inner workings will make that abundantly clear.

Be sure to also review an illustrated guide to how image-generating AIs work. And if a peek under the hood of LLMs left you hungry for more low-level details, check out our coverage of training a GPT-2 LLM using pure C code.

AI Helps Make Web Scraping Faster And Easier

May 8, 2024 by Donald Papp 13 Comments

Web scraping is usually only a first step towards extracting meaningful data. Once you’ve got everything pulled down, you’ve still got to process it into something useful. Here to assist with that is Scrapegraph-ai, a Python tool that promises to automate the process using a selection of large language models (LLMs).

Scrapegraph-ai is able to accept a URL as well as a prompt, which is a plain-English instruction on what to do with the data. Examples include summarizing, describing images, and more. In other words, gathering the data and analyzing or formatting it can now be done as one.

The project is actually pretty flexible in terms of the AI back-end. It’s able to work with locally-installed AI tools (via ollama) or with API keys for services like OpenAI and more. If you have an OpenAI API key, there’s an online demo that will show you the capabilities pretty effectively. Otherwise, local installation is only a few operations away.

This isn’t the first time we have seen the flexibility of AI tools like large language models leveraged to ease the notoriously-fiddly task of web scraping, and it’s great to see the results have only gotten better.