iiinova — where your digital self keeps evolving

Nous Research @nousresearch.com · 22/12/2025

Orders placed by US customers today will be shipped via Express air courier shipping and should arrive in time for Christmas so you can out-drip everyone at your family party and/or work function.

120

Nous Research @nousresearch.com · 22/12/2025

NOUS RESEARCH Q4 2025 DROP All items made entirely in the USA out of 100% cotton, featuring embroidery on the front and screen printing on the back. 1. "Good Technology" Super Heavy Weight Oversized Sweater 2. "Scaffolding" Tee 3. "Open Source" Tee shop.nousresearch.com/collections/...

120

Nous Research @nousresearch.com · 03/06/2025

Controlling text generation and structure remains a difficult problem to solve. Our newest blog post and release from Researcher in Residence @yaboilyrical (on Twitter) explores how this problem becomes solvable using Sequential Monte Carlo approximation. nousresearch.com/steering-the...

nousresearch.com

Steering the Shoggoth: Taming LLMs with Sequential Monte Carlo - NOUS RESEARCH

In this blog post, we present our findings from an exciting direction in controlling text generation with large language models. We can programmatically define constraints on the output of a model, en...

0100

Nous Research @nousresearch.com · 15/05/2025

Come join Nous and the Solana Foundation in NYC on Thursday, May 22nd, to discuss decentralized AI and Nous's efforts to democratize intelligence, including Psyche. Limited capacity. Apply below👇 lu.ma/39b7e9pu?v=1

lu.ma

Nous Research x Solana Foundation · Luma

Join Nous Research and the Solana Foundation for a private gathering in the Meatpacking District to discuss decentralized AI and Nous's efforts to democratize…

070

Nous Research @nousresearch.com · 14/05/2025

As always, we couldn't have gotten here without your help. Special thanks to our team, our community, and the open source movement.

010

Nous Research @nousresearch.com · 14/05/2025

Psyche’s initial training infrastructure is just the beginning of our journey. We plan to integrate full post training stages - supervised finetuning and reinforcement learning workloads, inference, and other parallelizable workloads in the creation and serving of AI going forward.

110

Nous Research @nousresearch.com · 14/05/2025

Looking ahead, we will draw model ideas from the community via our forum and Discord. By enabling highly parallel and scalable experimentation, we’re betting that the next innovation in model creation and design will come from the open source community

100

Nous Research @nousresearch.com · 14/05/2025

The resulting model will be small enough to train on a single H/DGX and run on a 3090, but will be powerful enough to serve as the basis for strong reasoning models and creative pursuits. The model will be trained continually without a final annealing step, resulting in a true unaltered base model.

100

Nous Research @nousresearch.com · 14/05/2025

We are launching testnet with the pre-training of a 40B parameter LLM: - MLA Architecture - Dataset consisting of FineWeb (14T) + FineWeb-2 minus some less common languages (4T), and The Stack v2 (1T)

40b parameters. 20t tokens. MLA architecture.

100

Nous Research @nousresearch.com · 14/05/2025

If you have 64+ H100 GPUs, Contact engineering@nousresearch.com to apply to provide hardware to the network’s training pool.

100

Nous Research @nousresearch.com · 14/05/2025

While compute on the network needs to be trusted and approved at this time, we plan to support trustless, community-owned compute resources. For now, open source enthusiasts can contribute via our mining pool, and we will be onboarding more nodes over the next weeks.

100

Nous Research @nousresearch.com · 14/05/2025

Psyche uses the Solana blockchain to decentralize parts of the core infrastructure for coordination and stores attestations for the nodes operating within the network. This design takes meaningful steps towards decentralization while ensuring training does not become too costly or redundant.

110

Nous Research @nousresearch.com · 14/05/2025

Training used to have a bandwidth constraint that kept the process centralized. In 2024, Nous's DisTrO optimizers broke through that constraint. With Psyche, we have created a custom peer-to-peer networking stack to coordinate globally distributed GPUs running DisTrO.

110

Nous Research @nousresearch.com · 14/05/2025

All the links! Blog: nousresearch.com/nous-psyche/ Training dashboard: psyche.network Code: github.com/PsycheFounda... Docs: docs.psyche.network Forum: forum.psyche.network HuggingFace: huggingface.co/PsycheFounda... Discord: discord.com/invite/jqVph...

nousresearch.com

Democratizing AI: The Psyche Network Architecture - NOUS RESEARCH

Psyche is an open infrastructure that democratizes AI development by decentralizing training across underutilized hardware. Building on DisTrO and its predecessor DeMo, Psyche reduces data transfer by...

110

Nous Research @nousresearch.com · 14/05/2025

This run represents the largest pre-training run conducted over the internet to date, surpassing previous iterations that trained smaller models on much fewer data tokens.

110

Nous Research @nousresearch.com · 14/05/2025

We are launching our testnet today with the pre-training of a 40B parameter LLM, a model powerful enough to serve as a foundation for future pursuits in open science.

120

Nous Research @nousresearch.com · 14/05/2025

Psyche is a decentralized training network that makes it possible to bring the world’s compute together to train powerful AI, giving individuals and small communities access to the resources required to create new, interesting, and unique large scale models.

120

Nous Research @nousresearch.com · 14/05/2025

Announcing the launch of Psyche nousresearch.com/nous-psyche/ Nous Research is democratizing the development of Artificial Intelligence. Today, we’re embarking on our greatest effort to date to make that mission a reality: The Psyche Network

A diagram of the Psyche network. It shows the relationship between the Solana Coordinator, an individual training client, the DisTrO optimizer inside a client, forward/backward passes to create gradients, the transmission and dissemination of the created DisTrO results, and the ingestion of data from a data provider.

1274

Nous Research @nousresearch.com · 13/03/2025

To ensure a smooth rollout, we made a waitlist: portal.nousresearch.com - Access will be granted on a first-come, first-served basis - Once granted access, you can create API keys and purchase credits - OpenAI-compatible API - Right now all accounts start off with $5.00 in free credits.

portal.nousresearch.com

Nous Portal

Nous Research is a leader in the development of human-centric language models and simulators. Manage your account and API keys here.

050

Nous Research @nousresearch.com · 13/03/2025

Today we’re releasing our Inference API that serves Nous Research models. We heard your feedback, and built a simple system to make our language models more accessible to developers and researchers everywhere. The initial release features two models - Hermes 3 Llama 70B and DeepHermes 3 8B Preview

portal.nousresearch.com

Nous Portal

Nous Research is a leader in the development of human-centric language models and simulators. Manage your account and API keys here.

170

Nous Research @nousresearch.com · 27/01/2025

Read more in our blog post: nousresearch.com/nous-psyche/

140

Nous Research @nousresearch.com · 27/01/2025

Recent AI breakthroughs challenge the status quo narrative that only closed, mega labs have the ability to push the frontier of superintelligence. Today we announce Nous Psyche built on @solana.com www.youtube.com/watch?v=XMWI...

youtube.com

The Story of Psyche

YouTube video by Nous Research

1195

Nous Research @nousresearch.com · 12/12/2024

Run Hermes on phones, laptops, and CPUs without sacrificing speed, and may also be a great pairing with 70B for speculative decoding! Learn more about Hermes, see our technical report, and chat with it now: nousresearch.com/hermes

nousresearch.com

Hermes 3 - NOUS RESEARCH

Hermes 3 contains advanced long-term context retention and multi-turn conversation capability, complex roleplaying and internal monologue abilities, and enhanced agentic function-calling. Our training...

090

Nous Research @nousresearch.com · 12/12/2024

Introducing a smol Hermes 3 LLM! Hermes 3 3B is now available on huggingface alongside quantized GGUF versions to make it even smaller. More info and download links here: huggingface.co/NousResearch... Hermes 3 3B was built by Teknium, Roger Jin, Jeffrey Quesnelle and "nullvaluetensor".

2294

Nous Research @nousresearch.com · 10/12/2024

Thursday December 12th Doors @ 6pm, Talks @ 7pm DCTRL, 436 W Pender St, Vancouver Open Entry. Food + Drink + Merch. DisTrO Demystified - Jeffrey Quesnelle , Bowen Peng Why Decentralization Matters - Mark Murdock Mapping Uncertainty at Inference Time - _xjdr

1151

Nous Research @nousresearch.com · 02/12/2024

We’re here to put the power of artificial intelligence into the hands of the many rather than the privileged few.

A graphic of the Nous Girl inside a circle. The graphic is blue and white. The circle has text wrapped around the edges that reads "REBELLION TO TYRANTS IS OBEDIENCE TO GOD."

3272

Nous Research @nousresearch.com · 02/12/2024

DeMo was created in March 2024 by Bowen Peng and Jeffrey Quesnelle and has been published on arXiv in collaboration with Diederik P. Kingma, co-founder of OpenAI and inventor of the Adam optimizer and VAEs. The paper is available here: arxiv.org/abs/2411.19870 And code: github.com/bloc97/DeMo

arxiv.org

DeMo: Decoupled Momentum Optimization

Training large neural networks typically requires sharing gradients between accelerators through specialized high-speed interconnects. Drawing from the signal processing principles of frequency decomp...

1152

Nous Research @nousresearch.com · 02/12/2024

We harness both Nous DisTrO, our novel networking stack that reduces inter-GPU communication by up to 10,000x during pretraining, and the testnet code for Psyche, a decentralized network that builds on Nous DisTrO to autonomously coordinate compute for model training. Psyche details coming soon.

170

Nous Research @nousresearch.com · 02/12/2024

This run presents a loss curve and convergence rate that meets or exceeds centralized training. Our paper and code on DeMo, the foundational research that led to Nous DisTrO, is now available (linked below).

170

Nous Research @nousresearch.com · 02/12/2024

Nous Research announces the pre-training of a 15B parameter language model over the internet, using Nous DisTrO and heterogeneous hardware contributed by our partners at Oracle, Lambda Labs, Northern Data Group, Crusoe, and the Andromeda Cluster. You can watch the run LIVE: distro.nousresearch.com

A screenshot of the Nous Distro website, showing training progress, a world map with some nodes marked and lines between them, and many graphs showing training progress.

79518

Nous Research @nousresearch.com · 12/11/2024

Elevating open-source ai to the level of frontier models has been a core principle of Nous since its inception. This technology requires testing & user feedback in order to determine what areas it uniquely excels at in the real world, so we have invited a small number of beta users to test it out.

170

Nous Research @nousresearch.com · 12/11/2024

The API is built upon three architectures developed at Nous: 1. Monte Carlo Tree Search (MCTS) 2. Chain of Code (CoC) 3. Mixture of Agents (MoA) Together, these three techniques create a powerful reasoning system that outputs complex, flexible, and nuanced responses from LLMs.

170

Nous Research @nousresearch.com · 12/11/2024

Today we are launching the Forge Reasoning API Beta, an advancement in inference time scaling that can be applied to any model. nousresearch.com/introducing-... The Forge Reasoning engine is capable of dramatically improving Hermes 70B to reach parity in some categories with OpenAI's o1 (full).

statistics showing hermes 3 70B with forge is a significant improvement over Hermes 3 70B

2284

Nous Research @nousresearch.com · 07/11/2024

We have reasoning enhancements, new models, and experimental capabilities planned for the future, and this will become the best place to experience Hermes and much more.

030

Nous Research @nousresearch.com · 07/11/2024

Since our first version of Hermes was released over a year ago, many people have asked for a place to experience it. Today we're happy to announce Nous Chat, a new user interface to experience Hermes 3 70B and beyond. hermes.nousresearch.com

1122