4 papers · 1 filter
Arcee Trinity Large Technical Report
Varun Singh, Lucas Krauss, Sami Jaghouar +23
We present the technical report for Arcee Trinity Large, a sparse Mixture-of-Experts model with 400B total parameters and 13B activated per token. Additionally, we report on Trinit…
INTELLECT-3: Technical Report
Prime Intellect Team, Mika Senghaas, Fares Obeid +20
We present INTELLECT-3, a 106B-parameter Mixture-of-Experts model (12B active) trained with large-scale reinforcement learning on our end-to-end RL infrastructure stack. INTELLECT-…
INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning
Prime Intellect Team, Sami Jaghouar, Justus Mattern +11
We introduce INTELLECT-2, the first globally distributed reinforcement learning (RL) training run of a 32 billion parameter language model. Unlike traditional centralized training…
OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training
Sami Jaghouar, Jack Min Ong, Johannes Hagemann
OpenDiLoCo is an open-source implementation and replication of the Distributed Low-Communication (DiLoCo) training method for large language models. We provide a reproducible imple…