paper-with-me

홈 › Papers

Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference

2023-03-08 · Chi Wang, Susan Xueqing Liu, Ahmed H. Awadallah

Large Language Models (LLMs) have sparked significant interest in their generative capabilities, leading to the development of various commercial applications. The high cost of using the models drives application builders to maximize the value of generation under a limited inference budget. This paper presents a study of optimizing inference hyperparameters such as the number of responses, temperature and max tokens, which significantly affects the utility/cost of text generation. We design a framework named EcoOptiGen which leverages economical hyperparameter optimization and cost-based pruning. Experiments with the GPT-3.5/GPT-4 models on a variety of tasks verify its effectiveness. EcoOptiGen is implemented in the `autogen' package of the FLAML library: \url{https://aka.ms/autogen}.

📄 PDF Abstract BibTeX arXiv:2303.04673

Code (3)

microsoft/FLAML 공식 구현
kevin666aa/flaml
qingyun-wu/autogen-eval pytorch

Tasks

Hyperparameter OptimizationLanguage ModelingLanguage ModellingLarge Language ModelText Generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…
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 &…
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…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

ACE: Adaptive Constraint-aware Early Stopping in Hyperparameter Optimization

2022-08-04 · Yi-Wei Chen, Chi Wang, Amin Saied, Rui Zhuang

Deploying machine learning models requires high model quality and needs to comply with application constraints. That motivates hyperparameter optimization (HPO) to tune model configurations under deployment constraints. …

FairnessHyperparameter Optimization

Start Small, Think Big: On Hyperparameter Optimization for Large-Scale Knowledge Graph Embeddings

2022-07-11 · Adrian Kochsiek, Fritz Niesel, Rainer Gemulla

Knowledge graph embedding (KGE) models are an effective and popular approach to represent and reason with multi-relational data. Prior studies have shown that KGE models are sensitive to hyperparameter settings, however,…

Graph EmbeddingHyperparameter OptimizationKnowledge Graph EmbeddingKnowledge Graph Embeddings+2

Tune As You Scale: Hyperparameter Optimization For Compute Efficient Training

2023-06-13 · Abraham J. Fetterman, Ellie Kitanidis, Joshua Albrecht, Zachary Polizzi 외

Hyperparameter tuning of deep learning models can lead to order-of-magnitude performance gains for the same amount of compute. Despite this, systematic tuning is uncommon, particularly for large models, which are expensi…

Bayesian OptimizationHyperparameter Optimization

Frugal Optimization for Cost-related Hyperparameters

2020-05-04 · Qingyun Wu, Chi Wang, Silu Huang

The increasing demand for democratizing machine learning algorithms calls for hyperparameter optimization (HPO) solutions at low cost. Many machine learning algorithms have hyperparameters which can cause a large variati…

AutoMLBIG-bench Machine LearningHyperparameter Optimization

Intrinsic Mutual Information as a Modulator for Preference Optimization

2026-04-27 · Peng Liao, Peijia Zheng, Lingbo Li, Shangsong Liang 외 arxiv

Offline preference optimization methods, such as Direct Preference Optimization (DPO), offer significant advantages in aligning Large Language Models (LLMs) with human values. However, achieving optimal performance with …