"Apertus: a fully open, transparent, multilingual language model
EPFL, ETH Zurich and the Swiss National Supercomputing Centre (CSCS) released Apertus 2 September, Switzerland’s first large-scale, open, multilingual language model — a milestone in generative AI for transparency and diversity.
Researchers from EPFL, ETH Zurich and CSCS have developed the large language model Apertus – it is one of the largest open LLMs and a basic technology on which others can build.
In brief Researchers at EPFL, ETH Zurich and CSCS have developed Apertus, a fully open Large Language Model (LLM) – one of the largest of its kind. As a foundational technology, Apertus enables innovation and strengthens AI expertise across research, society and industry by allowing others to build upon it. Apertus is currently available through strategic partner Swisscom, the AI platform Hugging Face, and the Public AI network. …
The model is named Apertus – Latin for “open” – highlighting its distinctive feature: the entire development process, including its architecture, model weights, and training data and recipes, is openly accessible and fully documented.
AI researchers, professionals, and experienced enthusiasts can either access the model through the strategic partner Swisscom or download it from Hugging Face – a platform for AI models and applications – and deploy it for their own projects. Apertus is freely available in two sizes – featuring 8 billion and 70 billion parameters, the smaller model being more appropriate for individual usage. Both models are released under a permissive open-source license, allowing use in education and research as well as broad societal and commercial applications. …
Trained on 15 trillion tokens across more than 1,000 languages – 40% of the data is non-English – Apertus includes many languages that have so far been underrepresented in LLMs, such as Swiss German, Romansh, and many others. …
Furthermore, for people outside of Switzerland, the external pagePublic AI Inference Utility will make Apertus accessible as part of a global movement for public AI. “Currently, Apertus is the leading public AI model: a model built by public institutions, for the public interest. It is our best proof yet that AI can be a form of public infrastructure like highways, water, or electricity,” says Joshua Tan, Lead Maintainer of the Public AI Inference Utility."
deleted by creator
Yes. Although they don’t host the dataset binaries.
Is this hosted somewhere? Maybe distributed? I would love a privacy respecting distributed LLM chatbot.
In case you’re not aware, there are a decent number of open weight (and some open source) large language models.
The Ollama project makes it very approachable to download and use these models.
Ollama has taken a bad turn lately (such is the nature of VC backed software). Maybe recommend
kobold.cppjan.ai for LLM noobs insteadI’m keeping an eye on Ollama’s service offerings - I don’t think they’re in enshittification territory yet, but I definitely share the concern.
I still don’t believe the other LLM engines out there have reached an equivalent ease of use compared to Ollama, and I still recommend it for now. If nothing else, it can be a stepping stone to other solutions for some.
Or just llama.cop they finally got an UI added
That’s what I use and also the backend of the aforementioned software, but it’s still complicated for people to set up.
I should also mention Jan, it makes things super easy and it also has a very nice GUI
Jan is another great recommendation!
there is nothing wrong with ollama it runs models fast and easy add a gguf and youre done unless you want to squeeze out extra performance and have time to figure out your exact flags then use llama cpp otherwise ollama just works for 99 percent of people
4.5/10 bait
if you send me a video of you completing the bussin level on geometry dash ill send you 10$
handcam necessary or just screen recording w clicks
screen recording 110715909
Other than Apertus, are there any truly open source models - mainly what I want to know is models that list their training data publicly to ensure no theft of art and stuff. (i replied to your comment as you seem to know about these models, I have no clue abou this stuff)
Deepseek R1 and OpenThinker are two more examples. There’s also SmolLM, which I believe also open sources its training data and ensures proper licensing for it.
Links in the article. Hugging Face and Swiss Telecoms host
I can’t find any hardware requirements for this. What will it take to run this smoothly?
8b parameter models are relatively fast on 3rd gen RTX hardware with at least 8gigs of vram, CPU inferencing is slower and requires boatloads of ram but is doable on older hardware. These really aren’t designed to run on consumer hardware, but the 8b model should do fine on relatively powerful consumer hardware.
If you have something that would’ve been a high end gaming rig 4 years ago, you’re good.
If you wanna be more specific, check huggingface, they have charts. If you’re using linux with nvidia hardware you’ll be better off doing CPU inferencing.
Edit: Omg y’all I didn’t think I needed to include my sources but this is quite literally a huge issue on nvidia. Nvidia works fine on linux but you’re limited to whatever VRAM is on your video card, no RAM sharing. Y’all can disagree all you want but those are the facts. Thays why AMD and CPU inferencing are more reliable, and allow for higher context limits. They are not faster though.
Sources for nvidia stuff https://github.com/NVIDIA/open-gpu-kernel-modules/discussions/618
https://forums.developer.nvidia.com/t/shared-vram-on-linux-super-huge-problem/336867/
https://github.com/NVIDIA/open-gpu-kernel-modules/issues/758
Thanks for the reply. Never been on the HF site and doing it on mobile of the first time I seem lost. I couldn’t find it but I’m sure I will.
Disagree on Linux nvidia support, it works fine
deleted by creator
For fastest inference, you want to fit the entire model in VRAM. Plus, you need a few GB extra for context.
Context means the text (+images, etc) it works on. That’s the chat log, in the case of a chatbot, plus any texts you might want summarized/translated/ask questions about.
Models can be quantized, which is a kind of lossy compression. They get smaller but also dumber. As with JPGs, the quality loss is insignificant at first and absolutely worth it.
Inference can be split between GPU and CPU, substituting VRAM with normal RAM. Makes it slower, but you’ll probably will still feel that it’s smooth.
Basically, it’s all trade-offs between quality, context size, and speed.
deleted by creator
Obligatory nitpick: open weights ≠ open source. For it to be open source, they need to release the training data as well as all the parameters they used in training it.
Please read the article before commenting.
“The model is named Apertus – Latin for “open” – highlighting its distinctive feature: the entire development process, including its architecture, model weights, and training data and recipes, is openly accessible and fully documented.”
Thanks… I have downvoted my own comment in shame. Godspeed!
a gentleperson and a scholar
Props to the humility!
Madlad
