🔥Telegram İfşa

We built the best EU-made LLM of its size! It supports all EU languages (and more), and beats Meta's Llama-3.1 on multilingual benchmarks. Congrats to everyone involved; super proud of this work.

The second, even better and bigger model is now out: EuroLLM-9B 🇪🇺 Ranks as the best open EU-made LLM of its size, proving competitive or superior when going up against models like Meta's Llama 3.1, Qwen 2.5, and Google's Gemma-2. Blog post & models: lnkd.in/d9JJvmd7

🚀 New paper alert! 🚀 Ever tried asking an AI about a 2-hour movie? Yeah… not great. Check: ∞-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation! 🔗 arxiv.org/abs/2501.19098 w/ Antonio Farinhas , Dan McNamee , Andre Martins

The position is advertised for 12 months, but it has the possibility of a further 2-year extension

New paper out 🚀 Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models: arxiv.org/abs/2504.01001. We present a framework and release a repository for creating reliable benchmarks for (V)LM tasks quickly and fully automatically.

Check out TREQA! TL;DR: We evaluate translation quality of complex content through QA using LLMs.

🚀 Big news! Tower+ is here — our strongest open-weight multilingual model yet!