Nous Research

In March 2024, we launched the Nous WorldSim project as an experiment in human-machine interactions. We explored how people could become immersed in a more human-like AI-simulated operating system. This version is a command-line interface (CLI) that allows users to create simulations of worlds, play games, or build rudimentary websites. Since its launch, Nous WorldSim has facilitated a significant number of long-form chat sessions and inspired a host of other philosophical, social, and animated simulators such as "yousim.ai" by Plastic Labs—a simulator game in which you can "explore the multiverse of identities" and talk to simulations of anyone or anything. It also inspired the "Infinite Backrooms," which led to the creation of "Truth Terminal” a viral Twitter account. The account’s associated memecoin is now approaching a value of close to a billion dollars in the span of only a few weeks. We're proud that our research and experimentation with our WorldSim project have become a catalyst for innovation, inspiring new technologies and experiences that are shaping the future of AI and human interaction! Play with WorldSim here: https://lnkd.in/gRTx4ibu Check out the original WorldSim prompt that our co-founder Karan Malhotra open-sourced here: https://lnkd.in/gine3s2k. Godspeed!

Why is open-source AI so important? Well… Nous Research made a great video showcasing why. "If you can't look inside the box and you don't trust the owner of the box, why do you think the box contains a safe AI"

Peak of anxiety when hearing “AI container orchestration”? 😅 See how simple it can be with dstack! Check this tutorial to deploy Nous Research Hermes 3 with dstack and vLLM, on Lambda: https://bit.ly/3UeYqfQ

It's always rewarding to see our work at Nous encourage people to build AI more openly! Ankit Pal at Open Life Science AI mentioned he was inspired by us to create the Medical Reasoning Tasks List, helping to advance AI in healthcare across diverse tasks: https://lnkd.in/gf-vhUt7 When we share our efforts in public forums, we often don't realize the positive impact they have across various industries. Freer information flow, fact-checking and democratic innovation propels our society forward. As Louis Pasteur said, "...knowledge belongs to humanity, and is the torch which illuminates the world."

Could the next big open source model be built by a global, distributed network of independent builders? We think it will be and are laying the groundwork for it to become a reality with DisTrO! Check out the AI + a16z podcast with Anjney Midha from a16z and Jeffrey Quesnelle and Bowen Peng from Nous Research as they dive into the technical breakthroughs behind DisTrO and explore how it could democratize AI development. Thanks for having us on! https://lnkd.in/gyjKjmyK a16z Andreessen Horowitz

Nous Research is hiring a Web Developer! For General Web Development Projects, Pages, and Payment Gateways. You will work on all web dev projects within Nous Research, including our primary website, merch store, and custom web applications that include use of AI API's, payment gateways, and custom applications for AI interfaces. We offer good wages, and a collaborative environment with intensely curious AI researchers. Interested candidates can email recruiting@nousresearch.com with their resume. For more details, send us a direct message here. We look forward to hearing from you!

Introducing a new open dataset release, Hermes Function Calling V1, the datamix that gave Hermes 2 Pro its tool use and structured output capabilities. HuggingFace Repo: https://lnkd.in/ex_smRtv The dataset includes single and multi-turn Function Calling and Structured JSON Output datasets, and an updated version of Glaive AI's function calling dataset, perfect for training LLMs to be better agents! Also check out our Hermes Function Calling repo for more information on the format and how to use models trained with this data here: https://lnkd.in/eqphH6fA And for help or questions, join our Discord! Here: https://lnkd.in/gnp7JnuQ This work is a culmination of the contributions of interstellar ninja, Teknium, Glaive AI, Theodore Galanos and many others who provided assistance along the way.

What if you could use all the computing power in the world to train a shared, open source AI model? The preliminary report: https://lnkd.in/eXpXUv-M Nous Research is proud to release a preliminary report on DisTrO (Distributed Training Over-the-Internet) a family of architecture-agnostic and network-agnostic distributed optimizers that reduces the inter-GPU communication requirements by 1000x to 10,000x without relying on amortized analysis, and matches AdamW+All-Reduce in convergence rates. This enables low-latency training of large neural networks on slow internet bandwidths with heterogeneous networking hardware. DisTrO can increase the resilience and robustness of training LLMs by minimizing dependency on a single entity for computation. DisTrO is one step towards a more secure and equitable environment for all participants involved in building LLMs. Without relying on a single company to manage and control the training process, researchers and institutions can have more freedom to collaborate and experiment with new techniques, algorithms, and models. This increased competition fosters innovation, drives progress, and ultimately benefits society as a whole. This research is thanks to the hard work of Bowen Peng, Jeffrey Quesnelle, Ari Lotter and Umer Adil. We invite researchers interested in exploring this area to join us in our quest!

🔥 Meet Hermes 3: The First Full-Parameter Fine-Tuning of Llama 3.1! 🧙♂️ ✍️ We’re excited to introduce Hermes 3, the first full-parameter fine-tune of Llama 3.1 405B, brought to you by Nous Research and trained on a Lambda 1-Click-Cluster. From strategic decision-making to complex creative writing, role-playing, and Agent building—Hermes 3 excels across the board. Try your prompts immediately on https://lambda.chat/ or use our Chat Completions API - for FREE.

The first Llama 3.1 405B fine-tuning was just completed by Nous Research on Lambda 1-Click Cluster. The outcome is Hermes 3, an unlocked and uncensored instruct model, which a/ follows user directions better and b/ scores as good or better than base model on benchmarks, even after quantization. That enables it to be served on a single 8x H100s node - for which we have on-demand availability and an amazing $2.99 / GPU / Hour price. All can prompt Hermes 3 for free on the https://lnkd.in/dZAMPWcb All can leverage the Lambda Completions API for free: https://lnkd.in/dCM_YEkQ We have a blog post out to bring our story together: https://lnkd.in/dvAf6RTT