👀May 1st DSPy with Weaviate • vector database, arize-phoenix, cohere

This doesn't look like anything to me..

Command R+
The Top Open-Weights LLM + RAG and Multilingual Support

My highlights on the release of the latest Cohere models and why I'm excited for LLM research.

newsletter.ruder.io/p/command-r

LLMs are finally breaking free from short context lengths using methods like Ring Attention.

Don't miss this visual explainer by Kilian Haefeli Simon Guo 🦝 Bonnie Li

Rerank is the fastest way to add a language model to a search system -- drastically improving its performance (with only one API call, and very low cost).

If you've built a RAG system, this is a great way to improve its retriever.

Awesome crowd!

مودل Command R Plus من cohere هو أجمل عيدية وربما أهم مودل بتطور نوعي جدا عن كل من سبقوه. مسافة ضوئية فعلاً.

من ذاق عرف ومن عرف اغترف ومن اغترف فقد بلغ المنزلة.

عيدكم مبارك جميعا وكل عام وأنتم طيبين 🎉

We're throwing 4 hackathons at each of our offices around the world!! If you're in NYC, London, Toronto, or SF come hang out with us and build with Command R and R+ 🛠️

We've prepared an excellent program that will have you building with some of the greatest LLM tools around.

Don't miss this one!

It's Time To Build

Let's build a 'Chat with your docs' RAG application, step-by-step:

Feeling real proud of the cohere team for this one. It’s a huge privilege to get to work with such a dedicated and talented team, and so rewarding to see that dedication and talent pay off :)

Also you should see the RAG and multi lingual performance ⌘

Exciting news - the latest Arena result are out!

cohere's Command R+ has climbed to the 6th spot, matching GPT-4-0314 level by 13K+ human votes! It's undoubtedly the **best** open model on the leaderboard now🔥

Big congrats to cohere's incredible work & valuable contribution…

There are 𝐭𝐰𝐨 benchmarks that I trust for LLMs:
- Your own evals 🔍
- Chatbot Arena 🤖 (users do a blind A/B test)

Amazing to see that Command R+ from cohere is the first open-weights model outperforming GPT-4.

And this is not yet testing RAG & tool use.

Hello QCon London Software Development Conference!

Excited to be here speaking about the most in-demand application of LLMs: Retrieval Augmented Generation (RAG).

Join me and my fellow co-speakers in the track 'What's Next in GenAI and Large Language Models (LLMs)' at #Qcon QCon Software Development Conferences

Great work from cohere on Command R+! Lots of ❤️ in our Discord:

In South America I saw this too A LOT

Many hotels, shops and office buildings had remote security people and doormen

You can see them and they can see you

Not sure where they work from but might as well be the cheapest country in South America (or the world!)

Remote jobs…

Azure will be the first cloud to offer Cohere's latest LLM, as we build on our commitment to offer customers the broadest selection of state of the art and open source models.

Cohere (cohere) just added another language model to the R suite: Command R+ 🥳

I'm so excited about the focus on RAG and tool use... along with the 128k-token context window AND its multi-lingual abilities.

I'm really happy to share a notebook building a RAG system with…

In a lot of other models, Arabic/اللغة العربية (and other non-English languages) are more expensive to use because the tokenizer basically punishes other languages by requiring a lot more tokens to represent their text.

Command R+ improves the tokenization, requiring less tokens…