Search results
bitnet.cpp is the official inference framework for 1-bit LLMs (e.g., BitNet b1.58). It offers a suite of optimized kernels, that support fast and lossless inference of 1.58-bit models on CPU (with NPU and GPU support coming next).
18 wrz 2024 · BitNet is an architecture introduced by Microsoft Research that uses extreme quantization, representing each parameter with only three values: -1, 0, and 1. This results in a model that uses just 1.58 bits per parameter, significantly reducing computational and memory requirements.
28 lut 2024 · Recent research, such as BitNet, is paving the way for a new era of 1-bit Large Language Models (LLMs). In this work, we introduce a 1-bit LLM variant, namely BitNet b1.58, in which every single parameter (or weight) of the LLM is ternary {-1, 0, 1}.
bitnet.cpp is the official inference framework for 1-bit LLMs (e.g., BitNet b1.58). It offers a suite of optimized kernels, that support fast and lossless inference of 1.58-bit models on CPU (with NPU and GPU support coming next).
26 mar 2024 · BitNet b1.58 addresses this by halving activation bits, enabling a doubled context length with the same resources, with potential further compression to 4 bits or lower for 1.58-bit LLMs, a...
BitNet b1.58 is based on the BitNet architecture, which is a Transformer that replaces nn.Linear with BitLinear. It is trained from scratch, with 1.58-bit weights and 8-bit activations.
5 sie 2024 · In recent developments, the BitNet b1.58 architecture has shown remarkable adaptability and efficiency, even when scaled down for smaller networks. This breakthrough addresses the growing need...
