Simon Willison’s Weblog

Subscribe

14 items tagged “finetuning”

2024

Introducing Apple’s On-Device and Server Foundation Models. Apple Intelligence uses both on-device and in-the-cloud models that were trained from scratch by Apple.

Their on-device model is a 3B model that "outperforms larger models including Phi-3-mini, Mistral-7B, and Gemma-7B", while the larger cloud model is comparable to GPT-3.5.

The language models were trained on unlicensed scraped data - I was hoping they might have managed to avoid that, but sadly not:

We train our foundation models on licensed data, including data selected to enhance specific features, as well as publicly available data collected by our web-crawler, AppleBot.

The most interesting thing here is the way they apply fine-tuning to the local model to specialize it for different tasks. Apple call these "adapters", and they use LoRA for this - a technique first published in 2021. This lets them run multiple on-device models based on a shared foundation, specializing in tasks such as summarization and proof-reading.

Here's the section of the Platforms State of the Union talk that talks about the foundation models and their fine-tuned variants.

As Hamel Husain says:

This talk from Apple is the best ad for fine tuning that probably exists.

The video also describes their approach to quantization:

The next step we took is compressing the model. We leveraged state-of-the-art quantization techniques to take a 16-bit per parameter model down to an average of less than 4 bits per parameter to fit on Apple Intelligence-supported devices, all while maintaining model quality.

Still no news on how their on-device image model was trained. I'd love to find out it was trained exclusively using licensed imagery - Apple struck a deal with Shutterstock a few months ago. # 11th June 2024, 3:44 pm

teknium/OpenHermes-2.5 (via) The Nous-Hermes and Open Hermes series of LLMs, fine-tuned on top of base models like Llama 2 and Mistral, have an excellent reputation and frequently rank highly on various leaderboards.

The developer behind them, Teknium, just released the full set of fine-tuning data that they curated to build these models. It’s a 2GB JSON file with over a million examples of high quality prompts, responses and some multi-prompt conversations, gathered from a number of different sources and described in the data card. # 1st February 2024, 4:18 am

2023

Fine-tuning GPT3.5-turbo based on 140k slack messages. Ross Lazerowitz spent $83.20 creating a fine-tuned GPT-3.5 turbo model based on 140,000 of his Slack messages (10,399,747 tokens), massaged into a JSONL file suitable for use with the OpenAI fine-tuning API.

Then he told the new model “write a 500 word blog post on prompt engineering”, and it replied “Sure, I shall work on that in the morning”. # 8th November 2023, 2:44 am

A Hackers’ Guide to Language Models. Jeremy Howard’s new 1.5 hour YouTube introduction to language models looks like a really useful place to catch up if you’re an experienced Python programmer looking to start experimenting with LLMs. He covers what they are and how they work, then shows how to build against the OpenAI API, build a Code Interpreter clone using OpenAI functions, run models from Hugging Face on your own machine (with NVIDIA cards or on a Mac) and finishes with a demo of fine-tuning a Llama 2 model to perform text-to-SQL using an open dataset. # 25th September 2023, 12:24 am

airoboros LMoE. airoboros provides a system for fine-tuning Large Language Models. The latest release adds support for LMoE—LoRA Mixture of Experts. GPT-4 is strongly rumoured to work as a mixture of experts—several (maybe 8?) 220B models each with a different specialty working together to produce the best result. This is the first open source (Apache 2) implementation of that pattern that I’ve seen. # 24th August 2023, 10:31 pm

Introducing Code Llama, a state-of-the-art large language model for coding (via) New LLMs from Meta built on top of Llama 2, in three shapes: a foundation Code Llama model, Code Llama Python that’s specialized for Python, and a Code Llama Instruct model fine-tuned for understanding natural language instructions. # 24th August 2023, 5:54 pm

Although fine-tuning can feel like the more natural option—training on data is how GPT learned all of its other knowledge, after all—we generally do not recommend it as a way to teach the model knowledge. Fine-tuning is better suited to teaching specialized tasks or styles, and is less reliable for factual recall. [...] In contrast, message inputs are like short-term memory. When you insert knowledge into a message, it’s like taking an exam with open notes. With notes in hand, the model is more likely to arrive at correct answers.

Ted Sanders, OpenAI # 15th April 2023, 1:44 pm

Replacing my best friends with an LLM trained on 500,000 group chat messages (via) Izzy Miller used a 7 year long group text conversation with five friends from college to fine-tune LLaMA, such that it could simulate ongoing conversations. They started by extracting the messages from the iMessage SQLite database on their Mac, then generated a new training set from those messages and ran it using code from the Stanford Alpaca repository. This is genuinely one of the clearest explanations of the process of fine-tuning a model like this I’ve seen anywhere. # 12th April 2023, 11:01 pm

gpt4all. Similar to Alpaca, here’s a project which takes the LLaMA base model and fine-tunes it on instruction examples generated by GPT-3—in this case, it’s 800,000 examples generated using the ChatGPT GPT 3.5 turbo model (Alpaca used 52,000 generated by regular GPT-3). This is currently the easiest way to get a LLaMA derived chatbot running on your own computer: the repo includes compiled binaries for running on M1/M2, Intel Mac, Windows and Linux and provides a link to download the 3.9GB 4-bit quantized model. # 29th March 2023, 6:03 pm

Hello Dolly: Democratizing the magic of ChatGPT with open models. A team at DataBricks applied the same fine-tuning data used by Stanford Alpaca against LLaMA to a much older model—EleutherAI’s GPT-J 6B, first released in May 2021. As with Alpaca, they found that instruction tuning took the raw model—which was extremely difficult to interact with—and turned it into something that felt a lot more like ChatGPT. It’s a shame they reused the license-encumbered 52,000 training samples from Alpaca, but I doubt it will be long before someone recreates a freely licensed alternative to that training set. # 24th March 2023, 5:05 pm

Fine-tune LLaMA to speak like Homer Simpson. Replicate spent 90 minutes fine-tuning LLaMA on 60,000 lines of dialog from the first 12 seasons of the Simpsons, and now it can do a good job of producing invented dialog from any of the characters from the series. This is a really interesting result: I’ve been skeptical about how much value can be had from fine-tuning large models on just a tiny amount of new data, assuming that the new data would be statistically irrelevant compared to the existing model. Clearly my mental model around this was incorrect. # 17th March 2023, 11:08 pm

Train and run Stanford Alpaca on your own machine. The team at Replicate managed to train their own copy of Stanford’s Alpaca—a fine-tuned version of LLaMA that can follow instructions like ChatGPT. Here they provide step-by-step instructions for recreating Alpaca yourself—running the training needs one or more A100s for a few hours, which you can rent through various cloud providers. # 16th March 2023, 4:10 pm

Stanford Alpaca, and the acceleration of on-device large language model development

Visit Stanford Alpaca, and the acceleration of on-device large language model development

On Saturday 11th March I wrote about how Large language models are having their Stable Diffusion moment. Today is Monday. Let’s look at what’s happened in the past three days.

[... 2055 words]

We introduce Alpaca 7B, a model fine-tuned from the LLaMA 7B model on 52K instruction-following demonstrations. Alpaca behaves similarly to OpenAI’s text-davinci-003, while being surprisingly small and easy/cheap to reproduce (<600$).

Alpaca: A Strong Open-Source Instruction-Following Model # 13th March 2023, 6:18 pm