MolmoAI

Want to bring this to the spotlight, we are currently (statsically) outperforming GPT-4o, Gemini 1.5 Pro & Claude 3.5 across 11 benchmarks! for more details check out our web 👇 molmo.me

Outperforming GPT-4o, Gemini 1.5 Pro & Claude 3.5 across 11 benchmarks! Only slightly surpassed by GPT-4o on the largest human preference study for VLMs with over 320k pairwise comparisons across nearly 1000 users

Study Solana DeFi

Would 100% agree that these are the preliminary applications of LLM for now - although just the tip of the iceberg!

Appreciate the love and support! We will definitely be the #unicorn of AI this cycle!

Catering to the international user base - did we mention that $MOLMO is scalable on @deepseek_ai 👀

Molmo is a repository for training and using Ai2's state-of-the-art multimodal open language models. Try $Molmo AI using our public demo showcasing the Molmo-7B-D model. molmo.allenai.org

Meet $MOLMOAI , the best fully open language model to date, including a family of 7B and 13B models trained up to 5T tokens. OLMo 2 outperforms other fully open models and competes with open-weight models like Llama 3.1 8B

@_m2rres_ @RaydiumProtocol We literally just sent 2% to our contributor, we have not locked yet so you are clearly wrong. Bundle as well, anyone that got in from the first few blocks on @pumpdotfun is flagged a sniper Please do your research and DD properly before spewing nonsense thank you

@MolmoLLM @RaydiumProtocol ye ye u bundled 50% and will only lock 3% what a retard

@_m2rres_ @RaydiumProtocol We will be doing so moving forward, please watch for the tweet

@MolmoLLM @RaydiumProtocol larp. didn't lock anything

@HustleMillenial posted!

@MolmoLLM github pls

We've released the OLMo 2 paper to kick off 2025 🔥. Including over 50 pages on 4 crucial components of the LLM development pipeline

We built $MOLMO by improving the stability of our long pretraining runs with changes to model architecture and training recipe. We also employ staged training, using learning rate annealing and introducing new, high-quality data (which we call Dolmino) at the end of pretraining

We developed ACE, a boundary-breaking climate emulator. Now, we introduce ACE2, which addresses stability and accuracy across a range of climates, broadening the scope of how AI can help us deal with climate change

We build AI that delivers real-world impact. From tackling wildland fires to improving understanding of climate change @MolmoLLM is dedicated to solving the world's biggest problems

With Molmo, all datasets were constructed without the use of VLMs

Training code, data, and everything you need to reproduce our models. Oh, and we have updated our tech report too! It's a great way to learn how to create VLMs like Molmo, or finetune our models!