Cost-Effective Hyperparameter Optimization for Large Language Model Generation InferenceDownload PDF

Published: 16 May 2023, Last Modified: 05 Sept 2023AutoML 2023 MainTrackReaders: Everyone
TL;DR: The first study of holistically optimizing the hyperparameters for text generation inference using large language models under budget constraints
Abstract: 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:
Keywords: Large Language Model, Text Generation, Hyperparameter Optimization
Submission Checklist: Yes
Broader Impact Statement: Yes
Paper Availability And License: Yes
Code Of Conduct: Yes
Reviewers: Yes
CPU Hours: 0
GPU Hours: 0
TPU Hours: 0
7 Replies