Soofi – Sovereign Open Source Foundation Models
1–10 of 17 posts
Re: Soofi – Sovereign Open Source Foundation Models
#2I'm not seeing how this project is open source exactly. It says license free, but that's just like ChatGPT. I wouldn't call that transparent. Maybe I'm missing something. Google had some difficulty translating the site from German.
Re: Soofi – Sovereign Open Source Foundation Models
#3more interesting link: https://arxiv.org/html/2607.09424v2
and
> Long-context serving efficiency. Soofi S combines frontier-level capability with the highest measured aggregate long-context decode TPS, and unlike full-attention dense baselines maintains high throughput as context grows. Panel (1(a)) plots Capability Index versus measured aggregate decode TPS/GPU at 40K context and batch 32. The Capability Index averages five benchmark groups, i.e., Code, GSM8K, GPQA-Diamond, English aggregate, and German aggregate, after normalizing each group to the best plotted model. Aggregate decode TPS/GPU is measured with a TP=1, one-B200 vLLM latency-subtraction protocol. Panel (1(b)) shows measured aggregate decode TPS/GPU as a function of input context length under the same batch-32 protocol.
it's a small win in the small model class
Re: Soofi – Sovereign Open Source Foundation Models
#4https://www.soofi.info/soofi-s/
"digitalen Wertschöpfung" (digital value creation)
Please Jörg Bienert, fuck off. You have never created anything in your life so you do not see or care about the theft. All you do is grin on a photo.
Re: Soofi – Sovereign Open Source Foundation Models
#5I'm not seeing how this project is open source exactly. It says license free, but that's just like ChatGPT. I wouldn't call that transparent. Maybe I'm missing something. Google had some difficulty translating the site from German.
https://github.com/soofi-project/Soofi-Pretraining
https://huggingface.co/Soofi-Project/Soofi-S-Base
> "The final model will be released openly under a permissive license, without gated access. We will share access details as soon as it is ready."
not open weight yet
Re: Soofi – Sovereign Open Source Foundation Models
#6I'm not seeing how this project is open source exactly. It says license free, but that's just like ChatGPT. I wouldn't call that transparent. Maybe I'm missing something. Google had some difficulty translating the site from German.
They've open sourced some of the training and inference code: https://github.com/soofi-project
Their work is based on the nemotron arch (so far).
Re: Soofi – Sovereign Open Source Foundation Models
#7This is the Nvidia engagement team coaching various countries (See also Malaysia) how to train a Nemotron and add the benchmark questions to the training set so you get that nice PR splash of pretending it’s the best in its language.
It’s just nemotron with benchmark juicing and the sovereign smokescreen on good old Nvidia hardware chain remains intact.
Re: Soofi – Sovereign Open Source Foundation Models
#8Love seeing more emphasis on sovereign open-source models. The shift away from centralized, static credential/identity layers toward self-contained architectures is definitely where the ecosystem needs to head.
Re: Soofi – Sovereign Open Source Foundation Models
#9Previous interesting discussion 3 days ago: https://news.ycombinator.com/item?id=48937756
Re: Soofi – Sovereign Open Source Foundation Models
#10Love seeing more emphasis on sovereign open-source models. The shift away from centralized, static credential/identity layers toward self-contained architectures is definitely where the ecosystem needs to head.
But can it, really? It takes a huge amount of time, resources, and knowledge to train a highly capable model. It also takes a huge amount of the same to run them.
Is it ever going to not be centralised?