Related papers: Getting Free Bits Back from Rotational Symmetries …
The rapid proliferation of large language models (LLMs) in natural language processing (NLP) has created a critical need for techniques that enable efficient deployment on memory-constrained devices without compromising performance. We…
While deep neural networks are a highly successful model class, their large memory footprint puts considerable strain on energy consumption, communication bandwidth, and storage requirements. Consequently, model size reduction has become an…
Although recent quantized Large Language Models (LLMs), such as BitNet, have paved the way for significant reduction in memory usage during deployment with binary or ternary weights, training these models still demands substantial memory…
As Large Language Models (LLMs) continue to grow in size, storing and transmitting them on edge devices becomes increasingly challenging. Traditional methods like quantization and pruning struggle to achieve extreme compression of LLMs…
1-bit LLM quantization offers significant advantages in reducing storage and computational costs. However, existing methods typically train 1-bit LLMs from scratch, failing to fully leverage pre-trained models. This results in high training…
Large Language Models (LLMs) are known for their expensive and time-consuming training. Thus, oftentimes, LLMs are fine-tuned to address a specific task, given the pretrained weights of a pre-trained LLM considered a foundation model. In…
In this paper, we propose a rotation-constrained compensation method to address the errors introduced by structured pruning of large language models (LLMs). LLMs are trained on massive datasets and accumulate rich semantic knowledge in…
We reduce the memory footprint of popular large-scale online learning methods by projecting our weight vector onto a coarse discrete set using randomized rounding. Compared to standard 32-bit float encodings, this reduces RAM usage by more…
Due to the substantial scale of Large Language Models (LLMs), the direct application of conventional compression methodologies proves impractical. The computational demands associated with even minimal gradient updates present challenges,…
Low-bit weight-only quantization significantly reduces the memory footprint of large language models (LLMs), but disproportionately affects certain examples. We analyze diverse 3-4 bit methods on LLMs ranging from 7B-70B in size and find…
State-of-the-art language models are becoming increasingly large in an effort to achieve the highest performance on large corpora of available textual data. However, the sheer size of the Transformer architectures makes it difficult to…
The large memory requirements of deep neural networks limit their deployment and adoption on many devices. Model compression methods effectively reduce the memory requirements of these models, usually through applying transformations such…
Large Language Models (LLMs) have long held sway in the realms of artificial intelligence research. Numerous efficient techniques, including weight pruning, quantization, and distillation, have been embraced to compress LLMs, targeting…
State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive for practical applications. Low-bit neural network…
Model quantification uses low bit-width values to represent the weight matrices of existing models to be quantized, which is a promising approach to reduce both storage and computational overheads of deploying highly anticipated LLMs.…
Large Language Models (LLMs) have enabled remarkable progress in natural language processing, yet their high computational and memory demands pose challenges for deployment in resource-constrained environments. Although recent low-rank…
Latent variable models have been successfully applied in lossless compression with the bits-back coding algorithm. However, bits-back suffers from an increase in the bitrate equal to the KL divergence between the approximate posterior and…
Due to their large size, generative Large Language Models (LLMs) require significant computing and storage resources. This paper introduces a new post-training quantization method, GPTQT, to reduce memory usage and enhance processing speed…
This paper starts with a simple lossless ~1.5:1 compression algorithm for the weights of the Large Language Model (LLM) Llama2 7B [1] that can be implemented in ~200 LUTs in AMD FPGAs, processing over 800 million bfloat16 numbers per…
Neural Machine Translation (NMT) is resource intensive. We design a quantization procedure to compress NMT models better for devices with limited hardware capability. Because most neural network parameters are near zero, we employ…