相关论文: Finer is Better (with the Right Scaling)

Mixed-precision quantization (MPQ) suffers from the time-consuming process of searching the optimal bit-width allocation i.e., the policy) for each layer, especially when using large-scale datasets such as ISLVRC-2012. This limits the…

The rapid development in the performance of large language models (LLMs) is accompanied by the escalation of model size, leading to the increasing cost of model training and inference. Previous research has discovered that certain layers in…

Training large language models with FP8 formats offers significant efficiency gains. However, the reduced numerical precision of FP8 poses challenges for stable and accurate training. Current frameworks preserve training performance using…

Large language models (LLMs) have achieved remarkable advancements in natural language processing, showcasing exceptional performance across various tasks. However, the expensive memory and computational requirements present significant…

Recent work has demonstrated that using a carefully designed sensing matrix rather than a random one, can improve the performance of compressed sensing. In particular, a well-designed sensing matrix can reduce the coherence between the…

Large Language Models (LLMs) have shown an impressive capability in code generation. The LLM effectiveness generally increases with its size: The higher the number of LLM's trainable parameters the better its ability to implement code.…

As Large Language Models (LLMs) scale, data curation has shifted from maximizing volume to optimizing the signal-to-noise ratio by performing quality filtering. However, for many languages, native high quality data is insufficient to train…

Although scaling laws and many empirical results suggest that increasing the size of Vision Transformers often improves performance, model accuracy and training behavior are not always monotonically increasing with scale. Focusing on…

Large language models (LLMs) are in need of sufficient contexts to handle many critical applications, such as retrieval augmented generation and few-shot learning. However, due to the constrained window size, the LLMs can only access to the…

Background: Large language models (LLMs) have greatly improved the accuracy of automated program repair (APR) methods. However, LLMs are constrained by high computational resource requirements. Aims: We focus on small language models…

Using fewer bits to represent model parameters and related tensors during pre-training has become a required technique for improving GPU efficiency without sacrificing accuracy. Microscaling (MX) formats introduced in NVIDIA Blackwell…

How does scaling the number of parameters in large language models (LLMs) affect their core capabilities? We study two natural scaling techniques -- weight pruning and simply training a smaller or larger model, which we refer to as dense…

Quantization has become one of the most effective methodologies to compress LLMs into smaller size. However, the existing quantization solutions still show limitations of either non-negligible accuracy drop or low system efficiency. In this…

Large language models (LLMs) bear promise as a fast and accurate material modeling paradigm for evaluation, analysis, and design. Their vast number of trainable parameters necessitates a wealth of data to achieve accuracy and mitigate…

Low-precision number formats are widely used in modern machine learning systems due to their efficiency. Accurate direction representation is key to the accuracy of vector operations. This work precisely explores the extent to which the…

Harmful fine-tuning attack poses serious safety concerns for large language models' fine-tuning-as-a-service. While existing defenses have been proposed to mitigate the issue, their performances are still far away from satisfactory, and the…

Post-training weight quantization is crucial for reducing the memory and inference cost of large language models (LLMs), yet pushing the average precision below 4 bits remains challenging due to highly non-uniform weight sensitivity and the…

We introduce methods to quantify how Large Language Models (LLMs) encode and store contextual information, revealing that tokens often seen as minor (e.g., determiners, punctuation) carry surprisingly high context. Notably, removing these…

As Large Language Models (LLMs) continue to advance in performance, their size has escalated significantly, with current LLMs containing billions or even trillions of parameters. However, in this study, we discovered that many layers of…

Large language models (LLMs) have emerged as powerful tools for addressing a wide range of general inquiries and tasks. Despite this, fine-tuning aligned LLMs on smaller, domain-specific datasets, critical to adapting them to specialized…