paper-with-me

홈 › Papers

Zebra: Extending Context Window with Layerwise Grouped Local-Global Attention

2023-12-14 · Kaiqiang Song, Xiaoyang Wang, Sangwoo Cho, Xiaoman Pan, Dong Yu

This paper introduces a novel approach to enhance the capabilities of Large Language Models (LLMs) in processing and understanding extensive text sequences, a critical aspect in applications requiring deep comprehension and synthesis of large volumes of information. Recognizing the inherent challenges in extending the context window for LLMs, primarily built on Transformer architecture, we propose a new model architecture, referred to as Zebra. This architecture efficiently manages the quadratic time and memory complexity issues associated with full attention in the Transformer by employing grouped local-global attention layers. Our model, akin to a zebra's alternating stripes, balances local and global attention layers, significantly reducing computational requirements and memory consumption. Comprehensive experiments, including pretraining from scratch, continuation of long context adaptation training, and long instruction tuning, are conducted to evaluate the Zebra's performance. The results show that Zebra achieves comparable or superior performance on both short and long sequence benchmarks, while also enhancing training and inference efficiency.

📄 PDF Abstract BibTeX arXiv:2312.08618

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Extending Context Window of Large Language Models from a Distributional Perspective

2024-10-02 · Yingsheng Wu, Yuxuan Gu, Xiaocheng Feng, Weihong Zhong 외

Scaling the rotary position embedding (RoPE) has become a common method for extending the context window of RoPE-based large language models (LLMs). However, existing scaling methods often rely on empirical approaches an…

16k8k

LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

2024-01-02 · Hongye Jin, Xiaotian Han, Jingfeng Yang, Zhimeng Jiang 외

It is well known that LLMs cannot generalize well to long contexts whose lengths are larger than the training sequence length. This poses challenges when employing LLMs for processing long input sequences during inferenc…

CoCA: Fusing Position Embedding with Collinear Constrained Attention in Transformers for Long Context Window Extending

2023-09-15 · Shiyi Zhu, Jing Ye, Wei Jiang, Siqiao Xue 외

Self-attention and position embedding are two key modules in transformer-based Large Language Models (LLMs). However, the potential relationship between them is far from well studied, especially for long context window e…

2kPosition

LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models

2024-08-31 · Zhiyuan Hu, Yuliang Liu, Jinman Zhao, Suyuchen Wang 외

Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended…

8kGPU

Understanding Neural Pathways in Zebrafish through Deep Learning and High Resolution Electron Microscope Data

2018-08-31 · Ishtar Nyawira, Kristi Bushman, Iris Qian, Annie Zhang

The tracing of neural pathways through large volumes of image data is an incredibly tedious and time-consuming process that significantly encumbers progress in neuroscience. We are exploring deep learning's potential to …

Deep LearningImage SegmentationSegmentationSemantic Segmentation