paper-with-me

Papers

Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference

2023-06-04 · Wangchunshu Zhou, Ronan Le Bras, Yejin Choi

Pre-trained Transformer models like T5 and BART have advanced the state of the art on a wide range of text generation tasks. Compressing these models into smaller ones has become critically important for practical use. Common neural network compression techniques such as knowledge distillation or quantization are limited to static compression where the compression ratio is fixed. In this paper, we introduce Modular Transformers, a modularized encoder-decoder framework for flexible sequence-to-sequence model compression. Modular Transformers train modularized layers that have the same function of two or more consecutive layers in the original model via module replacing and knowledge distillation. After training, the modularized layers can be flexibly assembled into sequence-to-sequence models that meet different performance-efficiency trade-offs. Experimental results show that after a single training phase, by simply varying the assembling strategy, Modular Transformers can achieve flexible compression ratios from 1.1x to 6x with little to moderate relative performance drop.

📄 PDF Abstract BibTeX arXiv:2306.02379

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderKnowledge DistillationModel CompressionNeural Network CompressionQuantizationText Generation

Methods 이 논문이 사용한 방법론

Gated Linear Unit A Gated Linear Unit, or GLU computes: $$ \mathrm{GLU}(a, b) = a \otimes \sigma(b) $$ It is used in natural language processing architectures, for example the Gated CNN,…
Attention 설명 없음
SentencePiece 설명 없음
Adafactor Adafactor is a stochastic optimization method based on Adam that reduces memory usage while retaining the empirical benefits of…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…

Similar Papers 제목 키워드 기반

Modularized Transfomer-based Ranking Framework

2020-04-28 · EMNLP 2020 11 · Luyu Gao, Zhuyun Dai, Jamie Callan

Recent innovations in Transformer-based ranking models have advanced the state-of-the-art in information retrieval. However, these Transformers are computationally expensive, and their opaque hidden states make it hard t…

Information RetrievalRetrieval

MICSim: A Modular Simulator for Mixed-signal Compute-in-Memory based AI Accelerator

2024-09-23 · Cong Wang, Zeming Chen, Shanshi Huang

This work introduces MICSim, an open-source, pre-circuit simulator designed for early-stage evaluation of chip-level software performance and hardware overhead of mixed-signal compute-in-memory (CIM) accelerators. MICSim…

Quantization

Modular addition without black-boxes: Compressing explanations of MLPs that compute numerical integration

2024-12-04 · Chun Hei Yip, Rajashree Agrawal, Lawrence Chan, Jason Gross

The goal of mechanistic interpretability is discovering simpler, low-rank algorithms implemented by models. While we can compress activations into features, compressing nonlinear feature-maps -- like MLP layers -- is an …

Numerical Integration

VDT: General-purpose Video Diffusion Transformers via Mask Modeling

2023-05-22 · Haoyu Lu, Guoxing Yang, Nanyi Fei, Yuqi Huo 외

This work introduces Video Diffusion Transformer (VDT), which pioneers the use of transformers in diffusion-based video generation. It features transformer blocks with modularized temporal and spatial attention modules t…

Autonomous DrivingVideo GenerationVideo Prediction

ExACT: An End-to-End Autonomous Excavator System Using Action Chunking With Transformers

2024-05-09 · Liangliang Chen, Shiyu Jin, Haoyu Wang, Liangjun Zhang

Excavators are crucial for diverse tasks such as construction and mining, while autonomous excavator systems enhance safety and efficiency, address labor shortages, and improve human working conditions. Different from th…

ChunkingImitation Learning