Check out our model release HERE
Meditron is the latest update to our suite of state-of-the-art open Large Medical Language Models trained from Llama-3.1 [8B] and [70B]
---
💯 OPEN weights released here 🔗 https://lnkd.in/eF8q9A94
🤝CO-DESIGNED: from day one with an interdisciplinary team of practicing clinicians from around the world, global humanitarian organizations, AI ethicists, and data scientists
📊STATE OF THE ART: Out-performing GPT4 on the standard medical benchmarks (*see footnote)
🌍REPRESENTATIVE: Continually pre-trained on an enormous corpus of expert-curated open-access medical literature and global clinical practice guidelines that is specifically inclusive of low-resource and humanitarian settings
🤖🤺 join a diverse global community of clinical experts 👩🏿⚕️🧑🏻⚕️👨🏼⚕️👩🏽⚕️🧑🏾⚕️👩🏼⚕️👨🏻⚕️ in the MOOVE. Sign up to show your interest here 🔗 https://lnkd.in/eQb3KyDc
--
Built with ❤️ by an incredible and mostly volunteer collaborative of
--💼Students and researchers at EPFL, Yale School of Medicine, and Carnegie Mellon University Africa
--⛑️Humanitarian advisors at the International Committee of the Red Cross - ICRC
--🏥Clinicians from across the world from Nairobi to Lausanne!
🏷️ Tagged in the comments by our phenomenal team lead Alexandre Sallinen
I am extremely lucky and grateful to work with you all ❤️
(*) While these benchmarks are helpful indicators of performance, we certainly can’t rely on results from static, hackable, generic multiple-choice questions from medical exams with a skewed geographic representation. medicineisnotmultiplechoice
We need robust, transparent real world representative expert evaluation in massive-scale clinical trials i.e.#jointhemoove 🇷🇼🇹🇿🇨🇭🇰🇪🇳🇬🇿🇦🇺🇸🇺🇬🇨🇦…Greetings from Kigali!
More models coming soon!
Σχόλια