Diego Peláez Paquico’s Post

View profile for Diego Peláez Paquico, graphic

AI & ML Engineer

Dream RAG LLM: - Good size for deploying in one A100 (35B params) - Multilingual - Tool use - Fine-tuned for grounding answers on the documents provided - Two citations modes for trade-offs in speed-quality - I guess that it must be good at refusing out of domain questions

View organization page for Cohere, graphic

138,717 followers

Introducing Command-R, our new RAG-optimized LLM aimed at large-scale production workloads. Command-R fits into the emerging “scalable” category of models that balance high efficiency with strong accuracy, enabling companies to move beyond proof of concept, and into production. Command-R is a generative model optimized for long context tasks such as retrieval augmented generation (RAG) and using external APIs and tools. It’s designed to work in concert with Cohere’s industry-leading Embed and Rerank models to provide best-in-class integration for RAG applications and excel at enterprise use cases — across the 10 major languages of the global market. Command-R will be available immediately on Cohere’s hosted API, and on major cloud providers in the near future. In keeping with Cohere’s core principles, it maintains a focus on privacy and data security. To learn more, visit our blog: https://lnkd.in/eUbSTyRr

Command R: RAG at Production Scale

Command R: RAG at Production Scale

txt.cohere.com

To view or add a comment, sign in

Explore topics