Several companies in the AI industry have released new open-source language models (LLMs) with advanced features. AI21Labs has scaled Jamba to a 256K context-window and released it as an open-weights model. Cohere, with contributions from various team members, has introduced a new LLM named Command R+ with capabilities such as multi-hop RAG, tool-use, and multilingual support. Command R+ is available on various platforms and has garnered praise for its features and open weights. Additionally, PSH_Lewis and pat_verga have highlighted the strengths of Command R+ in terms of RAG, tool-use, and multihop reasoning, emphasizing its release with open weights.
Wow, congrats @cohere on the exciting Command R+ release🔥 Another great contribution to open community! - 104B open weights, 128k context length - RAG, tool-use, multilingual Now, Command-R+ is in Arena accepting votes. Come challenge it with your toughest prompts! https://t.co/ljTqXJ5qcb https://t.co/pUnjNQ85sJ
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 is the new hero of open-source AI! Fantastic work from @aidangomez @sarahookr & team!
LLM Developers loved Command R, some called it the RAG King, well, hang on till you meet Command R+. Out now! Open weights. Much, much more capable: - Multi-hop RAG: It takes RAG capabilities to a whole new level, when dealing with complex questions, it’s able to search for… https://t.co/JVJ9hkrkSj
🚨 New model alert! Introducing Command R+! List of ingredients 🧑🏻🍳: - 128k-token context window - SOTA on advanced RAG with citations - multi-step Tool Use for task automation - multilingual in 10 major languages - available now on Azure, soon on OCI, Sagemaker and Bedrock, GCP,… https://t.co/zsu5c0Mn6F
Jamba from @AI21Labs scales to 256K context-window and is released as open-weights model. Will the hybrid Attention+Structured State Space models usher in a new era for open source LLMs? https://t.co/VqNNSb5kdl I explore this Q and more in this week's CoWI! Benchmarks 👇 https://t.co/2mYEeEYSAf