18 items tagged “meta”
2024
Ollama: Llama 3.2 Vision. Ollama released version 0.4 last week with support for Meta's first Llama vision model, Llama 3.2.
If you have Ollama installed you can fetch the 11B model (7.9 GB) like this:
ollama pull llama3.2-vision
Or the larger 90B model (55GB download, likely needs ~88GB of RAM) like this:
ollama pull llama3.2-vision:90b
I was delighted to learn that Sukhbinder Singh had already contributed support for LLM attachments to Sergey Alexandrov's llm-ollama plugin, which means the following works once you've pulled the models:
llm install --upgrade llm-ollama
llm -m llama3.2-vision:latest 'describe' \
-a https://static.simonwillison.net/static/2024/pelican.jpg
This image features a brown pelican standing on rocks, facing the camera and positioned to the left of center. The bird's long beak is a light brown color with a darker tip, while its white neck is adorned with gray feathers that continue down to its body. Its legs are also gray.
In the background, out-of-focus boats and water are visible, providing context for the pelican's environment.
That's not a bad description of this image, especially for a 7.9GB model that runs happily on my MacBook Pro.
Nous Hermes 3. The Nous Hermes family of fine-tuned models have a solid reputation. Their most recent release came out in August, based on Meta's Llama 3.1:
Our training data aggressively encourages the model to follow the system and instruction prompts exactly and in an adaptive manner. Hermes 3 was created by fine-tuning Llama 3.1 8B, 70B and 405B, and training on a dataset of primarily synthetically generated responses. The model boasts comparable and superior performance to Llama 3.1 while unlocking deeper capabilities in reasoning and creativity.
The model weights are on Hugging Face, including GGUF versions of the 70B and 8B models. Here's how to try the 8B model (a 4.58GB download) using the llm-gguf plugin:
llm install llm-gguf
llm gguf download-model 'https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B-GGUF/resolve/main/Hermes-3-Llama-3.1-8B.Q4_K_M.gguf' -a Hermes-3-Llama-3.1-8B
llm -m Hermes-3-Llama-3.1-8B 'hello in spanish'
Nous Research partnered with Lambda Labs to provide inference APIs. It turns out Lambda host quite a few models now, currently providing free inference to users with an API key.
I just released the first alpha of a llm-lambda-labs plugin. You can use that to try the larger 405b model (very hard to run on a consumer device) like this:
llm install llm-lambda-labs
llm keys set lambdalabs
# Paste key here
llm -m lambdalabs/hermes3-405b 'short poem about a pelican with a twist'
Here's the source code for the new plugin, which I based on llm-mistral. The plugin uses httpx-sse to consume the stream of tokens from the API.
Running Llama 3.2 Vision and Phi-3.5 Vision on a Mac with mistral.rs
mistral.rs is an LLM inference library written in Rust by Eric Buehler. Today I figured out how to use it to run the Llama 3.2 Vision and Phi-3.5 Vision models on my Mac.
[... 1,231 words]I think individual creators or publishers tend to overestimate the value of their specific content in the grand scheme of [AI training]. […]
We pay for content when it’s valuable to people. We’re just not going to pay for content when it’s not valuable to people. I think that you’ll probably see a similar dynamic with AI, which my guess is that there are going to be certain partnerships that get made when content is really important and valuable. I’d guess that there are probably a lot of people who have a concern about the feel of it, like you’re saying. But then, when push comes to shove, if they demanded that we don’t use their content, then we just wouldn’t use their content. It’s not like that’s going to change the outcome of this stuff that much.
Llama 3.2. In further evidence that AI labs are terrible at naming things, Llama 3.2 is a huge upgrade to the Llama 3 series - they've released their first multi-modal vision models!
Today, we’re releasing Llama 3.2, which includes small and medium-sized vision LLMs (11B and 90B), and lightweight, text-only models (1B and 3B) that fit onto edge and mobile devices, including pre-trained and instruction-tuned versions.
The 1B and 3B text-only models are exciting too, with a 128,000 token context length and optimized for edge devices (Qualcomm and MediaTek hardware get called out specifically).
Meta partnered directly with Ollama to help with distribution, here's the Ollama blog post. They only support the two smaller text-only models at the moment - this command will get the 3B model (2GB):
ollama run llama3.2
And for the 1B model (a 1.3GB download):
ollama run llama3.2:1b
I had to first upgrade my Ollama by clicking on the icon in my macOS task tray and selecting "Restart to update".
The two vision models are coming to Ollama "very soon".
Once you have fetched the Ollama model you can access it from my LLM command-line tool like this:
pipx install llm
llm install llm-ollama
llm chat -m llama3.2:1b
I tried running my djp codebase through that tiny 1B model just now and got a surprisingly good result - by no means comprehensive, but way better than I would ever expect from a model of that size:
files-to-prompt **/*.py -c | llm -m llama3.2:1b --system 'describe this code'
Here's a portion of the output:
The first section defines several test functions using the
@djp.hookimpl
decorator from the djp library. These hook implementations allow you to intercept and manipulate Django's behavior.
test_middleware_order
: This function checks that the middleware order is correct by comparing theMIDDLEWARE
setting with a predefined list.test_middleware
: This function tests various aspects of middleware:- It retrieves the response from the URL
/from-plugin/
using theClient
object, which simulates a request to this view.- It checks that certain values are present in the response:
X-DJP-Middleware-After
X-DJP-Middleware
X-DJP-Middleware-Before
[...]
I found the GGUF file that had been downloaded by Ollama in my ~/.ollama/models/blobs
directory. The following command let me run that model directly in LLM using the llm-gguf plugin:
llm install llm-gguf
llm gguf register-model ~/.ollama/models/blobs/sha256-74701a8c35f6c8d9a4b91f3f3497643001d63e0c7a84e085bed452548fa88d45 -a llama321b
llm chat -m llama321b
Meta themselves claim impressive performance against other existing models:
Our evaluation suggests that the Llama 3.2 vision models are competitive with leading foundation models, Claude 3 Haiku and GPT4o-mini on image recognition and a range of visual understanding tasks. The 3B model outperforms the Gemma 2 2.6B and Phi 3.5-mini models on tasks such as following instructions, summarization, prompt rewriting, and tool-use, while the 1B is competitive with Gemma.
Here's the Llama 3.2 collection on Hugging Face. You need to accept the new Llama 3.2 Community License Agreement there in order to download those models.
You can try the four new models out via the Chatbot Arena - navigate to "Direct Chat" there and select them from the dropdown menu. You can upload images directly to the chat there to try out the vision features.
Where Facebook’s AI Slop Comes From. Jason Koebler continues to provide the most insightful coverage of Facebook's weird ongoing problem with AI slop (previously).
Who's creating this stuff? It looks to primarily come from individuals in countries like India and the Philippines, inspired by get-rich-quick YouTube influencers, who are gaming Facebook's Creator Bonus Program and flooding the platform with AI-generated images.
Jason highlights this YouTube video by YT Gyan Abhishek (136,000 subscribers) and describes it like this:
He pauses on another image of a man being eaten by bugs. “They are getting so many likes,” he says. “They got 700 likes within 2-4 hours. They must have earned $100 from just this one photo. Facebook now pays you $100 for 1,000 likes … you must be wondering where you can get these images from. Don’t worry. I’ll show you how to create images with the help of AI.”
That video is in Hindi but you can request auto-translated English subtitles in the YouTube video settings. The image generator demonstrated in the video is Ideogram, which offers a free plan. (Here's pelicans having a tea party on a yacht.)
Jason's reporting here runs deep - he goes as far as buying FewFeed, dedicated software for scraping and automating Facebook, and running his own (unsuccessful) page using prompts from YouTube tutorials like:
an elderly woman celebrating her 104th birthday with birthday cake realistic family realistic jesus celebrating with her
I signed up for a $10/month 404 Media subscription to read this and it was absolutely worth the money.
Extracting Prompts by Inverting LLM Outputs (via) New paper from Meta research:
We consider the problem of language model inversion: given outputs of a language model, we seek to extract the prompt that generated these outputs. We develop a new black-box method, output2prompt, that learns to extract prompts without access to the model's logits and without adversarial or jailbreaking queries. In contrast to previous work, output2prompt only needs outputs of normal user queries.
This is a way of extracting the hidden prompt from an application build on an LLM without using prompt injection techniques.
The trick is to train a dedicated model for guessing hidden prompts based on public question/answer pairs.
They conclude:
Our results demonstrate that many user and system prompts are intrinsically vulnerable to extraction.
This reinforces my opinion that it's not worth trying to protect your system prompts. Think of them the same as your client-side HTML and JavaScript: you might be able to obfuscate them but you should expect that people can view them if they try hard enough.
SAM 2: The next generation of Meta Segment Anything Model for videos and images (via) Segment Anything is Meta AI's model for image segmentation: for any image or frame of video it can identify which shapes on the image represent different "objects" - things like vehicles, people, animals, tools and more.
SAM 2 "outperforms SAM on its 23 dataset zero-shot benchmark suite, while being six times faster". Notably, SAM 2 works with video where the original SAM only worked with still images. It's released under the Apache 2 license.
The best way to understand SAM 2 is to try it out. Meta have a web demo which worked for me in Chrome but not in Firefox. I uploaded a recent video of my brand new cactus tweezers (for removing detritus from my cacti without getting spiked) and selected the succulent and the tweezers as two different objects:
Then I applied a "desaturate" filter to the background and exported this resulting video, with the background converted to black and white while the succulent and tweezers remained in full colour:
Also released today: the full SAM 2 paper, the SA-V dataset of "51K diverse videos and 643K spatio-temporal segmentation masks" and a Dataset explorer tool (again, not supported by Firefox) for poking around in that collection.
One interesting observation is the impact of environmental factors on training performance at scale. For Llama 3 405B , we noted a diurnal 1-2% throughput variation based on time-of-day. This fluctuation is the result of higher mid-day temperatures impacting GPU dynamic voltage and frequency scaling.
During training, tens of thousands of GPUs may increase or decrease power consumption at the same time, for example, due to all GPUs waiting for checkpointing or collective communications to finish, or the startup or shutdown of the entire training job. When this happens, it can result in instant fluctuations of power consumption across the data center on the order of tens of megawatts, stretching the limits of the power grid. This is an ongoing challenge for us as we scale training for future, even larger Llama models.
llm-gguf. I just released a new alpha plugin for LLM which adds support for running models from Meta's new Llama 3.1 family that have been packaged as GGUF files - it should work for other GGUF chat models too.
If you've already installed LLM the following set of commands should get you setup with Llama 3.1 8B:
llm install llm-gguf
llm gguf download-model \
https://huggingface.co/lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf \
--alias llama-3.1-8b-instruct --alias l31i
This will download a 4.92GB GGUF from lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF on Hugging Face and save it (at least on macOS) to your ~/Library/Application Support/io.datasette.llm/gguf/models
folder.
Once installed like that, you can run prompts through the model like so:
llm -m l31i "five great names for a pet lemur"
Or use the llm chat
command to keep the model resident in memory and run an interactive chat session with it:
llm chat -m l31i
I decided to ship a new alpha plugin rather than update my existing llm-llama-cpp plugin because that older plugin has some design decisions baked in from the Llama 2 release which no longer make sense, and having a fresh plugin gave me a fresh slate to adopt the latest features from the excellent underlying llama-cpp-python library by Andrei Betlen.
I believe the Llama 3.1 release will be an inflection point in the industry where most developers begin to primarily use open source, and I expect that approach to only grow from here.
Introducing Llama 3.1: Our most capable models to date. We've been waiting for the largest release of the Llama 3 model for a few months, and now we're getting a whole new model family instead.
Meta are calling Llama 3.1 405B "the first frontier-level open source AI model" and it really is benchmarking in that GPT-4+ class, competitive with both GPT-4o and Claude 3.5 Sonnet.
I'm equally excited by the new 8B and 70B 3.1 models - both of which now support a 128,000 token context and benchmark significantly higher than their Llama 3 equivalents. Same-sized models getting more powerful and capable a very reassuring trend. I expect the 8B model (or variants of it) to run comfortably on an array of consumer hardware, and I've run a 70B model on a 64GB M2 in the past.
The 405B model can at least be run on a single server-class node:
To support large-scale production inference for a model at the scale of the 405B, we quantized our models from 16-bit (BF16) to 8-bit (FP8) numerics, effectively lowering the compute requirements needed and allowing the model to run within a single server node.
Meta also made a significant change to the license:
We’ve also updated our license to allow developers to use the outputs from Llama models — including 405B — to improve other models for the first time.
We’re excited about how this will enable new advancements in the field through synthetic data generation and model distillation workflows, capabilities that have never been achieved at this scale in open source.
I'm really pleased to see this. Using models to help improve other models has been a crucial technique in LLM research for over a year now, especially for fine-tuned community models release on Hugging Face. Researchers have mostly been ignoring this restriction, so it's reassuring to see the uncertainty around that finally cleared up.
Lots more details about the new models in the paper The Llama 3 Herd of Models including this somewhat opaque note about the 15 trillion token training data:
Our final data mix contains roughly 50% of tokens corresponding to general knowledge, 25% of mathematical and reasoning tokens, 17% code tokens, and 8% multilingual tokens.
Update: I got the Llama 3.1 8B Instruct model working with my LLM tool via a new plugin, llm-gguf.
2023
Meta/Threads Interoperating in the Fediverse Data Dialogue Meeting yesterday. Johannes Ernst reports from a recent meeting hosted by Meta aimed at bringing together staff from Meta’s Threads social media platform with representatives from the Fediverse.
Meta have previously announced an intention for Threads to join the Fediverse. It sounds like they’re being extremely thoughtful about how to go about this.
Two points that stood out for me:
“Rolling out a large node – like Threads will be – in a complex, distributed system that’s as decentralized and heterogeneous as the Fediverse is not something anybody really has done before.”
And:
“When we think of privacy risks when Meta connects to the Fediverse, we usually think of what happens to data that moves from today’s Fediverse into Meta. I didn’t realize the opposite is also quite a challenge (personal data posted to Threads, making its way into the Fediverse) for an organization as heavily monitored by regulators around the world as is Meta.”
Announcing Purple Llama: Towards open trust and safety in the new world of generative AI (via) New from Meta AI, Purple Llama is “an umbrella project featuring open trust and safety tools and evaluations meant to level the playing field for developers to responsibly deploy generative AI models and experiences”.
There are three components: a 27 page “Responsible Use Guide”, a new open model called Llama Guard and CyberSec Eval, “a set of cybersecurity safety evaluations benchmarks for LLMs”.
Disappointingly, despite this being an initiative around trustworthy LLM development,prompt injection is mentioned exactly once, in the Responsible Use Guide, with an incorrect description describing it as involving “attempts to circumvent content restrictions”!
The Llama Guard model is interesting: it’s a fine-tune of Llama 2 7B designed to help spot “toxic” content in input or output from a model, effectively an openly released alternative to OpenAI’s moderation API endpoint.
The CyberSec Eval benchmarks focus on two concepts: generation of insecure code, and preventing models from assisting attackers from generating new attacks. I don’t think either of those are anywhere near as important as prompt injection mitigation.
My hunch is that the reason prompt injection didn’t get much coverage in this is that, like the rest of us, Meta’s AI research teams have no idea how to fix it yet!
I’m banned for life from advertising on Meta. Because I teach Python. (via) If accurate, this describes a nightmare scenario of automated decision making.
Reuven recently found he had a permanent ban from advertising on Facebook. They won’t tell him exactly why, and have marked this as a final decision that can never be reviewed.
His best theory (impossible for him to confirm) is that it’s because he tried advertising a course on Python and Pandas a few years ago which was blocked because a dumb algorithm thought he was trading exotic animals!
The worst part? An appeal is no longer possible because relevant data is only retained for 180 days and so all of the related evidence has now been deleted.
Various comments on Hacker News from people familiar with these systems confirm that this story likely holds up.
Meta in Myanmar, Part I: The Setup. The first in a series by Erin Kissane explaining in detail exactly how things went so incredibly wrong with Facebook in Myanmar, contributing to a genocide ending hundreds of thousands of lives. This is an extremely tough read.
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.
Overture Maps Foundation Releases Its First World-Wide Open Map Dataset. The Overture Maps Foundation is a collaboration lead by Amazon, Meta, Microsoft and TomTom dedicated to producing “reliable, easy-to-use, and interoperable open map data”.
Yesterday they put out their first release and it’s pretty astonishing: four different layers of geodata, covering Places of Interest (shops, restaurants, attractions etc), administrative boundaries, building outlines and transportation networks.
The data is available as Parquet. I just downloaded the 8GB places dataset and can confirm that it contains 59 million listings from around the world—I filtered to just places in my local town and a spot check showed that recently opened businesses (last 12 months) were present and the details all looked accurate.
The places data is licensed under “Community Data License Agreement – Permissive” which looks like the only restriction is that you have to include that license when you further share the data.