paper-with-me

Papers

Fine-Tuning Pre-trained Transformers into Decaying Fast Weights

2022-10-09 · Huanru Henry Mao

Autoregressive Transformers are strong language models but incur O(T) complexity during per-token generation due to the self-attention mechanism. Recent work proposes kernel-based methods to approximate causal self-attention by replacing it with recurrent formulations with various update rules and feature maps to achieve O(1) time and memory complexity. We explore these approaches and find that they are unnecessarily complex, and propose a simple alternative - decaying fast weights - that runs fast on GPU, outperforms prior methods, and retains 99% of attention's performance for GPT-2. We also show competitive performance on WikiText-103 against more complex attention substitutes.

📄 PDF Abstract BibTeX arXiv:2210.04243

Code (1)

jenni-ai/t2fw 공식 구현 pytorch

Tasks

GPU

Methods 이 논문이 사용한 방법론

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…
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

s2s-ft: Fine-Tuning Pretrained Transformer Encoders for Sequence-to-Sequence Learning

2021-10-26 · Hangbo Bao, Li Dong, Wenhui Wang, Nan Yang 외

Pretrained bidirectional Transformers, such as BERT, have achieved significant improvements in a wide variety of language understanding tasks, while it is not straightforward to directly apply them for natural language g…

Abstractive Text SummarizationQuestion GenerationQuestion-GenerationText Generation

FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers

2022-11-15 · Jinyu Chen, Wenchao Xu, Song Guo, Junxiao Wang 외

Federated Learning (FL) is an emerging paradigm that enables distributed users to collaboratively and iteratively train machine learning models without sharing their private data. Motivated by the effectiveness and robus…

Federated LearningLanguage ModellingTransfer Learning

Finetuning Pretrained Transformers into Variational Autoencoders

2021-08-05 · EMNLP (insights) 2021 11 · Seongmin Park, Jihwa Lee

Text variational autoencoders (VAEs) are notorious for posterior collapse, a phenomenon where the model's decoder learns to ignore signals from the encoder. Because posterior collapse is known to be exacerbated by expres…

DecoderLanguage ModelingLanguage Modelling

Don't Sweep your Learning Rate under the Rug: A Closer Look at Cross-modal Transfer of Pretrained Transformers

2021-07-26 · Danielle Rothermel, Margaret Li, Tim Rocktäschel, Jakob Foerster

Self-supervised pre-training of large-scale transformer models on text corpora followed by finetuning has achieved state-of-the-art on a number of natural language processing tasks. Recently, Lu et al. (2021, arXiv:2103.…

Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers

2024-10-31 · Kai Yan, Alexander G. Schwing, Yu-Xiong Wang

Decision Transformers have recently emerged as a new and compelling paradigm for offline Reinforcement Learning (RL), completing a trajectory in an autoregressive way. While improvements have been made to overcome initia…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)