Search results
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.
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).
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}.
9 mar 2024 · 1.58 BitNet uses low-precision binary weights and quantized activations to 8 bits, and high-precision for optimizer states and gradient functions during training. It can be represented as a...
26 mar 2024 · Unlike its predecessor, BitNet b1.58 replaces the conventional nn.Linear layers with BitLinear layers, leveraging 1.58-bit weights and 8-bit activations.
29 lut 2024 · BitNet b1.58 emerges as a solution, utilizing 1-bit ternary parameters to dramatically lighten the load on computational resources while maintaining high model performance. This section will...
29 lut 2024 · Unlike its predecessors, BitNet b1.58 is trained from the ground up, utilizing weights quantized to 1.58-bits and activations reduced to 8-bits. This approach significantly deviates from the standard full-precision formats typically seen in AI models.
