September 5, 2023
Jais: a New Pinnacle in Open Arabic NLP
Introducing a new state-of-the-art bi-lingual…
July 24, 2023
BTLM-3B-8K: 7B Performance in a 3 Billion Parameter Model
Cerebras and Opentensor introduce a new standard for…
July 20, 2023
Introducing Condor Galaxy 1: a 4 exaFLOPS Supercomputer for Generative AI
Cerebras, in partnership with G42 unveils CG-1, a 4…
June 9, 2023
SlimPajama: A 627B token, cleaned and deduplicated version of RedPajama
Today we are releasing SlimPajama – the largest…
May 22, 2023
Cerebras Architecture Deep Dive: First Look Inside the HW/SW Co-Design for Deep Learning [Updated]
Our ML-optimized architecture enables the largest models to…
March 28, 2023
Cerebras-GPT: A Family of Open, Compute-efficient, Large Language Models
Cerebras open sources seven GPT-3 models from 111 million…
November 28, 2022
Harnessing the Power of Sparsity for Large GPT AI Models
Enabling innovation of novel sparse ML techniques to…
August 15, 2022
Context is Everything: Why Maximum Sequence Length Matters
GPU-Impossible™ sequence lengths on Cerebras systems may…