🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Excited to share the results of our collaboration with Nous Research to launch the pre-training of a 15B parameter language model over the internet, powered by our hardware. True innovation thrives when technology is available to all. Find out more here: distro.nousresearch.com

welcome to the fam s8n

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 - a cooperative training network for generative AI. Psyche coordinates heterogeneous

they should’ve given the $500b to Nous

Today Nous announced the coming of Psyche - a distributed network and training framework, an infrastructure layer for training Open AI Models over the internet built around our distro breakthrough. The new reasoning paradigm that we've entered with a lot of help from

x.com/i/article/1907…

If you want to work with me at Nous, we've got an opening for a very good 𝒻𝓇𝑜𝓃𝓉 𝑒𝓃𝒹 𝒹𝑒𝓋 𝑒𝓁𝑜𝓅𝑒𝓇. I have to write it like that so bots don't spam my messages. But yes, feel free to message me and apply.

We are hiring MLOps, Front End, and more. E-Mail [email protected] with your CV or check our website’s job board for more info nousresearch.com/careers/

Announcing the Nous RL Environments Hackathon in SF! Create with Atropos, Nous' RL environments framework, and claim your stake of a $50,000 prize pool. Partners - xAI NVIDIA Nebius SHACK15 Akash Network Lambda TensorStax and RunPod May 18th. Sign up below 👇👇

I’m pleased to announce Lambda’s (LambdaClass) new strategic partnership with Nous Research (Nous Research). We will work as hard as possible to support Nous Research in their fight for freedom in AI.

Come hack with us!

Psyche's out 🔥

My guy cooked

world's first 40B CC0-licensed model with DeepSeek MLA trained across dozens of data centers over the internet and the loss just keeps going down 400 h100s online now, 800 imminent

Huge fan of Nous Research. Was a big inspiration behind building Alpaca Network & modelz We couldnt be more aligned on the mission accelerate intelligence + human flourishing. Anyone who cares about the future of AI should watch this talk by Dill

In case the post was too vague, yes - this is the Hermes 3 dataset - 1 Million Samples - Created SOTA without the censorship at it's time on Llama-3 series (8, 70, and 405B) - Has a ton of data for teach system prompt adherence, roleplay, and a great mix of subjective and

Join the team behind the decentralized training projects Psyche and DisTrO for an office hours session in Nous Research's discord - Thursday evening, 6PM PST Discord Link: discord.gg/NousResearch

Looks like OpenAI's been using Nous' YaRN and kaiokendev's rope scaling for context length extension all along - of course never any credit but... Anyone who says "open source just steals from their 'real' research and rides on their shoulders" is completely wrong I called it

a small sample of what our big dense model CoTs can look like internally