Výsledky vyhledávání

Report

QAQ: Quality Adaptive Quantization for LLM KV Cache

Autor: Dong, Shichen, Cheng, Wen, Qin, Jiayu, Wang, Wei

The emergence of LLMs has ignited a fresh surge of breakthroughs in NLP applications, particularly in domains such as question-answering systems and text generation. As the need for longer context grows, a significant bottleneck in model deployment e

Externí odkaz: http://arxiv.org/abs/2403.04643

Zobrazit plný text záznamu

Report

Learning Unnormalized Statistical Models via Compositional Optimization

Autor: Jiang, Wei, Qin, Jiayu, Wu, Lingyu, Chen, Changyou, Yang, Tianbao, Zhang, Lijun

Learning unnormalized statistical models (e.g., energy-based models) is computationally challenging due to the complexity of handling the partition function. To eschew this complexity, noise-contrastive estimation~(NCE) has been proposed by formulati

Externí odkaz: http://arxiv.org/abs/2306.07485

Zobrazit plný text záznamu

Report

Prompt Tuning based Adapter for Vision-Language Model Adaption

Autor: Sun, Jingchen, Qin, Jiayu, Lin, Zihao, Chen, Changyou

Large pre-trained vision-language (VL) models have shown significant promise in adapting to various downstream tasks. However, fine-tuning the entire network is challenging due to the massive number of model parameters. To address this issue, efficie

Externí odkaz: http://arxiv.org/abs/2303.15234

Zobrazit plný text záznamu