paper-with-me

Papers

Generative Parameter-Efficient Fine-Tuning

2023-12-01 · Chinmay Savadikar, Xi Song, Tianfu Wu

We present Generative Parameter-Efficient Fine-Tuning (GIFT) for adapting pretrained Transformer backbones on downstream tasks. GIFT learns to generate the fine-tuned weights for a layer directly from its pretrained weights. The GIFT network is parameterized in a minimally-simple way by two linear layers (without bias terms), and is shared by different pretrained layers selected for fine-tuning (e.g., the Query layers), which result in significantly fewer trainable parameters compared to the layer-specific methods like Low-Rank Adapter (LoRA). We also show this formulation bridges parameter-efficient fine-tuning and representation fine-tuning. We perform comprehensive experiments on natural language tasks (commonsense and arithmetic reasoning, instruction tuning, and sequence classification) and computer vision tasks (fine-grained classification). We obtain the best performance and parameter efficiency among baselines on commonsense and arithmetic reasoning, and instruction following using the Llama family of models and on visual recognition benchmarks using Vision Transformers. Notably, compared to LoRA, we obtain 5.7% absolute increase in average accuracy with 14 times reduction of parameters on Commonsense170k using Llama-3 (8B), and 5.4% absolute increase in the win rate with 4 times reduction of parameters using Llama-2 (7B) during instruction tuning. Our GIFT also obtains a slightly higher win rate on instruction tuning than GPT 3.5 (Turbo 1106).

📄 PDF Abstract BibTeX arXiv:2312.00700

Code (1)

savadikarc/gift 공식 구현 pytorch

Tasks

Arithmetic ReasoningFine-Grained Image ClassificationInstruction Followingparameter-efficient fine-tuningSemantic Segmentation

Methods 이 논문이 사용한 방법론

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 &…
LLaMA LLaMA is a collection of foundation language models ranging from 7B to 65B parameters. It is based on the transformer architecture with various improvements that were…
Adapter 설명 없음
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…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Weight Decay 설명 없음
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…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…

Similar Papers 제목 키워드 기반

Source-Prior-Driven Selective Adaptation for Efficient Diffusion Model Finetuning

2026-07-23 · Yi Xiong, Yuan-Yuan Cheng, Xiao-Ming Fu arxiv

Fine-tuning large diffusion models for new domains or styles involves a trade-off: improving target-specific generation often degrades the pretrained model's broad generative capability. Existing full and parameter-effic…

parameter-efficient fine-tuning

Exploring Versatile Generative Language Model Via Parameter-Efficient Transfer Learning

2020-04-08 · Findings of the Association for Computational Linguistics 2020 · Zhaojiang Lin, Andrea Madotto, Pascale Fung

Fine-tuning pre-trained generative language models to down-stream language generation tasks has shown promising results. However, this comes with the cost of having a single, large model for each task, which is not ideal…

Language ModelingLanguage ModellingText GenerationTransfer Learning

Robust and Efficient Fine-tuning of LLMs with Bayesian Reparameterization of Low-Rank Adaptation

2024-11-07 · Ayan Sengupta, Vaibhav Seth, Arinjay Pathak, Natraj Raman 외

Large Language Models (LLMs) are highly resource-intensive to fine-tune due to their enormous size. While low-rank adaptation is a prominent parameter-efficient fine-tuning approach, it suffers from sensitivity to hyperp…

Natural Language Understandingparameter-efficient fine-tuningparameter estimation

Automatic Summarization of Doctor-Patient Encounter Dialogues Using Large Language Model through Prompt Tuning

2024-03-19 · Mengxian Lyu, Cheng Peng, Xiaohan Li, Patrick Balian 외

Automatic text summarization (ATS) is an emerging technology to assist clinicians in providing continuous and coordinated care. This study presents an approach to summarize doctor-patient dialogues using generative large…

Language ModelingLanguage ModellingLarge Language ModelText Summarization

Parameter-Efficient Finetuning of Transformers for Source Code

2022-12-12 · Shamil Ayupov, Nadezhda Chirkova

Pretrained Transformers achieve state-of-the-art performance in various code-processing tasks but may be too large to be deployed. As software development tools often incorporate modules for various purposes which may po…

parameter-efficient fine-tuning