相关论文: Self-Distilled Quantization: Achieving High Compre…

Spoken question answering (SQA) is a challenging task that requires the machine to fully understand the complex spoken documents. Automatic speech recognition (ASR) plays a significant role in the development of QA systems. However, the…

Fine-tuned transformer models have shown superior performances in many natural language tasks. However, the large model size prohibits deploying high-performance transformer models on resource-constrained devices. This paper proposes a…

Dataset Distillation (DD) compresses large datasets into compact synthetic ones that maintain training performance. However, current methods mainly target sample reduction, with limited consideration of data precision and its impact on…

As the rapid scaling of large language models (LLMs) poses significant challenges for deployment on resource-constrained devices, there is growing interest in extremely low-bit quantization, such as 2-bit. Although prior works have shown…

Large language models (LLMs) face significant computational and memory challenges, making extremely low-bit quantization crucial for their efficient deployment. In this work, we introduce SDQ-LLM: Sigma-Delta Quantization for 1-bit LLMs of…

Quality Estimation (QE) is the task of automatically predicting Machine Translation quality in the absence of reference translations, making it applicable in real-time settings, such as translating online social media conversations. Recent…

Post-training quantization (PTQ) has emerged as a promising technique to reduce the cost of large language models (LLMs). Specifically, PTQ can effectively mitigate memory consumption and reduce computational overhead in LLMs. To meet the…

Large language models (LLMs) deliver strong performance, but their high compute and memory costs make deployment difficult in resource-constrained scenarios. Weight-only post-training quantization (PTQ) is appealing, as it reduces memory…

Large language models~(LLMs) have recently demonstrated promising performance in many tasks. However, the high storage and computational cost of LLMs has become a challenge for deploying LLMs. Weight quantization has been widely used for…

As Large Language Models (LLMs) become increasingly computationally complex, developing efficient deployment strategies, such as quantization, becomes crucial. State-of-the-art Post-training Quantization (PTQ) techniques often rely on…

Sequence-level knowledge distillation (SLKD) is a model compression technique that leverages large, accurate teacher models to train smaller, under-parameterized student models. Why does pre-processing MT data with SLKD help us train…

Post-training model quantization is a widely adopted technique for reducing the memory and computational costs of large language models (LLMs). However, most existing methods rely on uniform or heuristic bitwidth assignments, failing to…

In the past few years, transformer-based pre-trained language models have achieved astounding success in both industry and academia. However, the large model size and high run-time latency are serious impediments to applying them in…

Quantization has emerged as a mainstream approach for deploying Large Language Models (LLMs) on resource-constrained devices, yet compressing precision below 4-bit typically causes severe performance degradation or prohibitive retraining…

Emergent Large Language Models (LLMs) use their extraordinary performance and powerful deduction capacity to discern from traditional language models. However, the expenses of computational resources and storage for these LLMs are stunning,…

Large Language Models (LLMs) have demonstrated exceptional code generation capabilities, yet their token-level mechanisms remain underexplored, particularly in compressed models. Through systematic analysis of programming language token…

Deploying large language models (LLMs) in resource-constrained environments is hindered by heavy computational and memory requirements. We present LBLLM, a lightweight binarization framework that achieves effective W(1+1)A4 quantization…

Pre-trained language-vision models have shown remarkable performance on the visual question answering (VQA) task. However, most pre-trained models are trained by only considering monolingual learning, especially the resource-rich language…

Knowledge Distillation (KD) is a commonly used technique for improving the generalization of compact Pre-trained Language Models (PLMs) on downstream tasks. However, such methods impose the additional burden of training a separate teacher…

Weight-only quantization has become a standard approach for efficiently serving large language models (LLMs). However, existing methods fail to efficiently compress models to binary (1-bit) levels, as they either require large amounts of…