Tag
4 articles
Soofi Consortium releases Soofi S 30B-A3B, an open hybrid Mamba-Transformer MoE model for German and English. The model leverages 3.2 billion active parameters out of 31.6 billion for efficient multilingual processing.
This article explains the concept of hybrid vision-language models, focusing on how Zyphra's Zamba2-VL combines Mamba2 and Transformer architectures to dramatically improve processing speed.
Researchers are combining Transformer architectures with NetKet and JAX to solve complex frustrated spin systems, advancing quantum machine learning applications.
Amazon is reportedly developing a new smartphone code-named 'Transformer' that will center around its Alexa AI assistant, marking a strategic return to the mobile market after the failure of the Fire Phone.
