Memory requirements are the most obvious advantage of reducing the complexity of a model's internal weights. The BitNet b1.58 ...

The BitNet b1.58 2B4T model was developed by Microsoft's General Artificial Intelligence group and contains two billion parameters – internal values that enable the model to ...

Microsoft's BitNet challenges industry norms with a minimalist approach using ternary weights that require just 400MB of ...

Microsoft’s General Artificial Intelligence group has introduced a groundbreaking large language model (LLM) that drastically ...

Microsoft’s new BitNet b1.58 model significantly reduces memory and energy requirements while matching the capabilities of ...

Trained on 4 trillion tokens, this open-source model rivals full-precision LLMs in performance while offering impressive ...

Microsoft Research has introduced BitNet b1.58 2B4T, a new 2-billion parameter language model that uses only 1.58 bits per ...

Huawei Technologies has applied for a patent in “ternary logic”, an alternative to binary computing logic first explored in the former Soviet Union, in hopes that it could improve the design ...

It could count to several thousand using a balanced ternary mechanical mechanism. The [Fowler] machine was used to calculate logs, and the usual boring mathematical tasks of the time. A bit more ...

Two? What is two? A ternary, or base-3, computer would be odd, disturbing, but nevertheless extremely interesting, making it a great candidate for The Hackaday Prize. A base-3 computer isn’t a ...