Log inSign up
Sergey Edunov
103 posts
user avatar
Sergey Edunov
@edunov
CTO @ Genesis Molecular AI. Ex: AI Research Director @ Meta
Joined March 2010
185
Following
2,224
Followers

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • user avatar
    Sergey Edunov
    @edunov
    Sep 12, 2024
    Every time someone asks what's next for Llama
    51K
  • user avatar
    Sergey Edunov
    @edunov
    Apr 18, 2024
    Yes, Llama 3 is INSANE
    MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF · OK llama 3 8b model is INSANE. Is almost as good as...
    From huggingface.co
    26K
  • user avatar
    Sergey Edunov
    @edunov
    Apr 21, 2024
    People seem to over-index on the 15T number after Llama 3. While the number matters, what is even more important is the quality and diversity of those tokens. If there was a good way to measure those, that would have been an impressive result to report.
    user avatar
    Thomas Wolf
    @Thom_Wolf
    Apr 21, 2024
    Llama3 was trained on 15 trillion tokens of public data. But where can you find such datasets and recipes?? Here comes the first release of 🍷Fineweb. A high quality large scale filtered web dataset out-performing all current datasets of its scale. We trained 200+ ablation
    207K
  • user avatar
    Sergey Edunov
    @edunov
    Aug 9, 2024
    Fascinating, how entire LLM industry is chasing ELO score on lmsys, just recently it was Open LLM leaderboard and MMLU, and still around those who remember the days of GLUE and SuperGLUE. Meanwhile Goodhart's law never gets old: "When a measure becomes a target, it ceases to be
    18K
  • user avatar
    Sergey Edunov
    @edunov
    Apr 19, 2024
    The real king is still training 💪😝 But go go go 70B and 8B!
    user avatar
    Arena.ai
    @arena
    Apr 19, 2024
    Early 1K votes are in and Llama-3 is on FIRE!🔥The New king of OSS model? Vote now and make your voice heard! Leaderboard update coming very soon.
    20K
  • user avatar
    Sergey Edunov
    @edunov
    Apr 25, 2024
    There are many ways a very large and powerful model can be useful, even if no one can run it locally today: Distillation -- think about all recent results people show distilling GPT-4 outputs and training smaller models on those, how much more can be done if the teacher model
    user avatar
    Louis-François Bouchard 🎥🤖
    @Whats_AI
    Apr 25, 2024
    I really love Meta’s open-source focus, but I doubt many of us will leverage such big models. None of us will run Llama3 400B locally 😅 Using APIs stays the way most of us will interact and work with LLMs. But Llama-3 8B or even 70B is quite cool, haha! Still, open sourcing
    23K
  • user avatar
    Sergey Edunov
    @edunov
    Jul 23, 2024
    Article cover image
    Article
    The Llama 3 Herd of Models
    The Llama 3 Herd of Models is has just arrived! What do we have to share? Three model sizes: the already familiar 8B and 70B with new goodies like 128k context window and multilingual support, as...
    11K
  • user avatar
    Sergey Edunov
    @edunov
    Apr 18, 2024
    Llama 3 has arrived! Taaa-daaam!
    ai.meta.com
    Introducing Meta Llama 3: The most capable openly available LLM to date
    Today, we’re introducing Meta Llama 3, the next generation of our state-of-the-art open source large language model. In the coming months, we expect to share new capabilities, additional model sizes,...
    11K
  • user avatar
    Sergey Edunov
    @edunov
    Apr 30, 2024
    How come long context adaptions of Llama 3 that are being released only report performance on long context benchmarks? Do we assume that context extension happens for free without impacting model performance? Show us your MMLU, GSM8K, ARC-C and DROP!
    8.8K
  • user avatar
    Sergey Edunov
    @edunov
    May 1, 2024
    Congrats @teknium and the team, amazing work! I've been waiting for it 😉
    user avatar
    Nous Research
    @NousResearch
    May 1, 2024
    Announcing Hermes 2 Pro on Llama-3 8B! Nous Research's first Llama-3 based model is now available on HuggingFace. Hermes Pro comes with Function Calling and Structured Output capabilities, and the Llama-3 version now uses dedicated tokens for tool call parsing tags, to make
    11K
  • user avatar
    Sergey Edunov
    @edunov
    May 4, 2024
    MMLU is particularly tricky. - how do you prompt matters a lot - changes in the order of answers in 5-shot examples matter - whether you use logits or model generations matters - do you micro-average or macro-average matters - it is also quite noisy It all works out okay
    user avatar
    Percy Liang
    Together AI
    @percyliang
    May 3, 2024
    How should you prompt an LM for MMLU? (You could say MMLU is contaminated/saturated and we should just use vibes, but that’s a separate conversation. As long as people are bragging about their MMLU scores, we should make sure we know what these scores mean). Two extremes:
    7.5K
  • user avatar
    Sergey Edunov
    @edunov
    Jun 5, 2024
    In our past lives we did machine translation 😅 Happy to share that this work is now published in Nature.
    user avatar
    Marta R. Costa-jussa
    @costajussamarta
    Jun 5, 2024
    It is been a long team journey, and our NLLB work is now published in Nature. Proud of having being part of successfully scaling translation to 200 languages: nature.com/articles/s4158…
    2.3K
  • user avatar
    Sergey Edunov
    @edunov
    Apr 22, 2024
    So so so excited about these results
    user avatar
    Arena.ai
    @arena
    Apr 22, 2024
    Replying to @arena
    Moreover, we observe even stronger performance in English category, where Llama 3 ranking jumps to ~1st place with GPT-4-Turbo! It consistently performs strong against top models (see win-rate matrix) by human preference. It's been optimized for dialogue scenario with large
    3.1K
  • user avatar
    Sergey Edunov
    @edunov
    Apr 18, 2024
    Llama 3 to the moon 🚀 😉
    user avatar
    Jim Fan
    @DrJimFan
    Apr 18, 2024
    The upcoming Llama-3-400B+ will mark the watershed moment that the community gains open-weight access to a GPT-4-class model. It will change the calculus for many research efforts and grassroot startups. I pulled the numbers on Claude 3 Opus, GPT-4-2024-04-09, and Gemini.
    7.5K