相关论文: On the Impact of Calibration Data in Post-training…

Recent work has shown that layer pruning can effectively compress large language models (LLMs) while retaining strong performance on classification benchmarks, often with little or no finetuning. In contrast, generative reasoning tasks,…

Multimodal Large Language Models (MLLMs) have shown strong reasoning ability, but their high computational and memory costs hinder deployment in resource-constrained settings. While Post-Training Quantization (PTQ) and vision token pruning…

Transformer-based NLP models are trained using hundreds of millions or even billions of parameters, limiting their applicability in computationally constrained environments. While the number of parameters generally correlates with…

It has been observed in practice that applying pruning-at-initialization methods to neural networks and training the sparsified networks can not only retain the testing performance of the original dense models, but also sometimes even…

As large language models attract increasing attention and find widespread application, concurrent challenges of reliability also arise at the same time. Confidence calibration, an effective analysis method for gauging the reliability of…

Structured pruning is widely used to compress large language models (LLMs), yet its effectiveness depends heavily on neuron importance estimation. Most existing methods estimate neuron importance from activation statistics on a single…

Layer pruning efficiently reduces Large Language Model (LLM) computational costs but often triggers sudden performance collapse. Existing representation-based analyses struggle to explain this mechanism. We propose studying pruning through…

Confidence calibration -- the problem of predicting probability estimates representative of the true correctness likelihood -- is important for classification models in many applications. We discover that modern neural networks, unlike…

Large language models (LLMs) have demonstrated remarkable performance across a wide range of industrial applications, from search and recommendation systems to generative tasks. Although scaling laws indicate that larger models generally…

While Multimodal Large Language Models (MLLMs) demonstrate impressive capabilities, their substantial computational and memory requirements pose significant barriers to practical deployment. Current parameter reduction techniques primarily…

Large Language Models (LLMs) have achieved remarkable success across a wide spectrum of natural language processing tasks. However, their ever-growing scale introduces significant barriers to real-world deployment, including substantial…

With time, machine learning models have increased in their scope, functionality and size. Consequently, the increased functionality and size of such models requires high-end hardware to both train and provide inference after the fact. This…

Pretrained large language models (LLMs) exhibit exceptional general language processing capabilities but come with significant demands on memory and computational resources. As a powerful compression technology, binarization can extremely…

While scaling laws for large language models (LLMs) during pre-training have been extensively studied, their behavior under reinforcement learning (RL) post-training remains largely unexplored. This paper presents a systematic empirical…

This study examines quantisation and pruning strategies to reduce energy consumption in code Large Language Models (LLMs) inference. Using StarCoder2, we observe increased energy demands with quantization due to lower throughput and some…

Large Language Models (LLMs) have demonstrated impressive reasoning capabilities, but their substantial size often demands significant computational resources. To reduce resource consumption and accelerate inference, it is essential to…

Large language models (LLMs) demonstrate strong performance as text embedding models when finetuned with supervised contrastive training. However, their large size balloons inference time and memory requirements. In this paper, we show that…

Deep neural networks have been the predominant paradigm in machine learning for solving cognitive tasks. Such models, however, are restricted by a high computational overhead, limiting their applicability and hindering advancements in the…

Increasing the number of parameters in large language models (LLMs) usually improves performance in downstream tasks but raises compute and memory costs, making deployment difficult in resource-limited settings. Quantization techniques,…

Large pre-trained language models (PLMs) have demonstrated strong performance on natural language understanding (NLU) tasks through fine-tuning. However, fine-tuned models still suffer from overconfident predictions, especially in…