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).
This is a reproduction of the BitNet b1.58 paper. The models are trained with RedPajama dataset for 100B tokens. The hypers, as well as two-stage LR and weight decay, are implemented as suggested in their following paper. All models are open-source in the repo.
18 wrz 2024 · While pre-training models in 1.58 bits is resource-intensive, we’ve demonstrated that, with some tricks, it’s possible to fine-tune existing models to this precision level, achieving efficient performance without sacrificing accuracy.
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}.
4 kwi 2024 · BitNet b1.58 continues to match full-precision Transformer LLM baselines in both perplexity and end-task performance, all while demonstrating cost-effectiveness in terms of latency, memory,...
24 cze 2024 · We introduce a variant of BitNet b1.58, which allows to rely on the median rather than the mean in the quantization process. Through extensive experiments we investigate the performance of 1.58-bit models obtained through quantization aware training.
