Cohere AI has launched a new state-of-the-art model named Command R Plus, marking a significant advancement in the field of artificial intelligence. This model introduces an advanced Retrieval-Augmented Generation (RAG) system with citations to minimize hallucinations, supports 10 languages, and boasts a context length of 128K. It is available for free testing, highlighting its open-source nature and the company's commitment to research and safety in AI. The development team, including notable figures such as Aidan Gomez and Sarah Hooker, has received widespread acclaim for their work, with the AI community hailing Command R Plus as a groundbreaking achievement in open-source AI. The model's capabilities in RAG, tool use, and multilingual support are particularly emphasized, alongside its cost-effectiveness and the dedication of the team behind it. The release of state-of-art weights for research use aims to power exciting research and critical safety work across the ecosystem. Command R Plus is described as the world's best and most capable open weight model, with its open weights being a key feature. Pat Verga announced he joined Cohere seven months ago, contributing to the development of this great model.
Building RAG with Command R+ from Cohere, DSPy, and Weaviate! https://t.co/PCniHMFftA via @YouTube
Working on local RAG using great open models and easy touchpoints command-r by @cohere via @ollama for generation (great prompt docs too: https://t.co/jaUdXkI0a3) nomic-embed-text by @nomic_ai via @ollama for embedding retrieval with @trychroma https://t.co/9Hldx2hhGG
Command-R+ is currently the most prominent & hottest release in Technology around the world! Congratulations team @cohere! 🪅🥳
More exciting news from @cohere! ⌘R+ is out now, check out it 🔥🔥🔥 https://t.co/JuLlOBiHhU
With #RAG being all the rage right now, there are so many different solutions out there -- how do you choose your stack? Check out this blog post from @AI21Labs about their RAG Engine and Contextual Answers #TSM to see what their particular solution offers 👀 https://t.co/CEpCptNknZ
✅ state-of-the-art ✅ plays well with tools ✅ multilingual ✅ cost-effective ✅ open weights ✅ built by people who really care what's not to love about ⌘R+ ? proud of @cohere and @CohereForAI today and everyday https://t.co/xLIezaXt1D
Building a RAG solution is easy. Building a great one is not. In our guest blog on @streamlit, our team explores the intricacies of how AI21's Contextual Answers Task-Specific Model & our RAG Engine generate context-based answers grounded in your proprietary organizational data.…
As RAG gets more complicated, it starts to look more agentic 🤖 @cohere released a new open weights (!!) model that is a perfect fit for this @RLanceMartin made a killer video on it - check it out below thanks to @aidangomez and everyone at cohere for this!! https://t.co/x9V3imyIOw
Adaptive RAG w/ Cohere's new Command-R+ Adaptive-RAG (@SoyeongJeong97 et al) is a recent paper that combines (1) query analysis and (2) iterative answer construction to seamlessly handle queries of differing complexity. We took at stab at implementing these ideas from scratch… https://t.co/eDz1TMaBqf
Adaptive RAG 🧠🔎 Not all questions are created equal. RAG techniques that do well on simple questions will fail on complex multi-step ones; fancy agentic techniques that address the latter will be way slower for simple questions. Adaptive RAG is a cool paper by @SoyeongJeong97… https://t.co/hFu7agKPCB
Pleased to announce that I've joined @cohere (7 months ago...) Since then we've built a great model (excellent at RAG, tooluse and multihop reasoning) that we are releasing along with the weights today! https://t.co/IW3R5pXcwv
🚨 🚨 ⌘R+ Our new state-of-the-art LLM. It is multilingual, amazing at RAG and tool-use 🔥 Enjoy its open weights as well. Super proud to be part of @cohere @CohereForAI. https://t.co/wNyT20V1Kh
⌘R and, now, ⌘R+ are available now, including their weights!🥁🥁🥁 They are great combining RAG, Citing and tool-use - a really powerful combo. I am particularly passionate about grounded generation with citations/attribution (may tweet more on this soon!). Check them out! https://t.co/sjPyoH9hr3
🚨Cohere AI has launched a new model, Command R Plus, 1. Advanced (RAG) with citations to reduce hallucinations. 2. Supports 10 languages. 3. Context length of 128K. Test this model for free and all the details you need to know in 🧵 https://t.co/hYKHyaU05E
Cohere is the new hero of open-source AI! Fantastic work from @aidangomez @sarahookr & team!
⌘R+ ✨🤩🥳🚀 Super exciting to finallyyy share our Command R+ with the world! It’s bigger, better, and more powerful on RAG, Tool Use and Multilingual! 🎊🎉 Even more exciting it’s the world’s best and most capable open weight model 🔝✨ https://t.co/fdCuN9R6C6
Really proud of our continued commitment across @cohere @CohereForAI to release state-of-art weights for research use. ✨ Excited we get to share a state-of-art model which I hope will power exciting research and critical safety work across the ecosystem. 🔥 https://t.co/ASr2GwCV0E