We trained a ~frontier Deep Research Agent on academic budget > 32 H100s

We trained a ~frontier Deep Research Agent on academic budget > 32 H100s > 8K synthetic samples > fully open training infra + recipe (SFT, mid-training, RL) > models of diff sizes (2B -> 35B) ready to use out of the box This is yet another demonstration of how the frontier of AI is changing. We have reached a point where open models + a small capable team + a few hundred Ks can produce specialized models with ~frontier capabilities. The future of AI doesn’t have to be held in a chokehold by a handful of closed models. We've open-sourced everything we've built and learned from this project. Hope it helps the community build more! 📌 Project: 📌 Paper: 📌 Code: 📌 Model Weights and Data: 📌 Demo: Amazing effort led by @jianxie_ (our 1st year student!!), Tianhe Lin, Zilu Wang. joint with @hhsun1 and the @osunlp team. thanks @amazon Xiangjun Wang for a gift that covers the compute and fruitful discussion.

We trained a ~frontier Deep Research Agent on academic budget > 32 H100s

Source

You might also wanna read

EXCLUSIVE: Biden Administration Buried Intel Whistleblower Complaint Accusing Fauci of Lying to Congress, by @DisInfoChron

Gabbard releases documents alleging Fauci steered intelligence away from lab leak theory investigation

Fictional ODNI Release Alleges Fauci Funded Wuhan Lab Research as COVID-19 Source

Buy EA SPORTS™ UFC 6 - Electronic Arts

Note #59: Taking care of your mental health Make peace with the hard days. I see a lot of people stuck in a victim mentality. The truth is hard days are not the enemy. resistance to them is. the momen

🚨🚨@DNIGabbard “Today, on my final day as Director of National Intelligence, I’m releasing never-before-seen communications and documents exposing how Dr. Fauci provided millions in US taxpayer dolla