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).
This repository not only provides PyTorch implementations for training and evaluating 1.58-bit neural networks but also includes a unique integration where the experiments conducted automatically update a LaTeX-generated paper.
9 mar 2024 · 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 “w2a8”...
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...
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 - WIP! Based on Microsoft's 'The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits' paper. This repository introduces a toy work-in-progress implementation of BitNet - a scalable and stable 1-bit Transformer architecture designed specifically for large language models.
