Benchmarks? Edit: Thanks, @Bengalilol. The 1.7B one looks meh. But really solid numbers on the 9B! Props to the team!
EuroLLM: LLM made in Europe built to support all 24 official EU languages
11–20 of 629 posts
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#12Are there any benchmarks that exist for those 24 languages?
dupe of https://news.ycombinator.com/item?id=45733832
which sank to the bottom thanks to HN's invisible hand
Oh wait, one's not supposed to notice
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#13It's just another Horizon2020 grant, people. Don't be overly harsh to a bunch of academics who are just earning their living.
I didn't know of the grant!
https://research-and-innovation.ec.europa.eu/funding/funding...
It seems the new version is called Horizon Europe
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#14I was thinking the same, why are so many superior models coming from only countries like US and China. And why are European countries not in the list other than France with Mistral. Why are so few companies in India, Japan, South Korea even close to a promising new model like what Chinese companies did ?
Does it even make sense? Just use the American or Chinese ones, adjust
As needed. Where’s the point in spending millions to build
The same thing or worse
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#15I was thinking the same, why are so many superior models coming from only countries like US and China. And why are European countries not in the list other than France with Mistral. Why are so few companies in India, Japan, South Korea even close to a promising new model like what Chinese companies did ?
Because training frontier model is expensive and only US and China have capital structure to raise tens of billions of dollars to do it.
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#16For those curious, the 24 official languages are Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Irish, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Slovak, Slovenian, Spanish, and Swedish. Maltese, interestingly, is the only Afro-Asiatic derived language. Hungarian, Finnish, and Estonian are the three Uralic languages. All the others ar…
I read, write and speak Maltese, AMA if you are curious about the language.
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#17>The EuroLLM Team brings together some of the brightest minds in AI including Unbabel, Instituto Tecnico Lisbon, the University of Edinburgh, Instituto de Telecommunicacoes, Université Paris-Saclay, Aveni, Sorbonne University, Naver Labs, and the University of Amsterdam.
>Europe is the only continent in the world to have a large public network of supercomputers that are managed by the EuroHPC Joint Undertaking (EuroHPC JU). As soon as we received the EuroHPC JU access to the supercomputer, we were ready to roll up our sleeves and get to work. We developed the small model right away and in less than 6 months the second model was ready.
[1] https://www.eurohpc-ju.europa.eu/eurohpc-success-story-speak...
Repurposing some of that physics sim compute
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#18If I want to use an LLM to do translation, should I use a base model or an instruction tuned version? I've had mixed results using the chat models and a simple "Translate this to : "
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#19Could you adjust the title from: "all official 24 EU languages” to "all 24 official EU languages"
The former is used on the website itself.
Re: EuroLLM: LLM made in Europe built to support all 24 official EU languages
#20Aren't all frontier models already able to use all these languages? Support for specific languages doesn't need to be built in, LLMs support all languages because they are trained on multilingual data.
> because they are trained on multilingual data
But they were not trained on government-sanctioned homegrown EU data.