Benchmarking quantized LLaMa-based models on the Brazilian Secondary School Exam

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Santos, Matheus L. O., Campelo, Cláudio E. C.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913073605902336
author Santos, Matheus L. O.
Campelo, Cláudio E. C.
author_facet Santos, Matheus L. O.
Campelo, Cláudio E. C.
contents Although Large Language Models (LLMs) represent a revolution in the way we interact with computers, allowing the construction of complex questions and the ability to reason over a sequence of statements, their use is restricted due to the need for dedicated hardware for execution. In this study, we evaluate the performance of LLMs based on the 7 and 13 billion LLaMA models, subjected to a quantization process and run on home hardware. The models considered were Alpaca, Koala, and Vicuna. To evaluate the effectiveness of these models, we developed a database containing 1,006 questions from the ENEM (Brazilian National Secondary School Exam). Our analysis revealed that the best performing models achieved an accuracy of approximately 46% for the original texts of the Portuguese questions and 49% on their English translations. In addition, we evaluated the computational efficiency of the models by measuring the time required for execution. On average, the 7 and 13 billion LLMs took approximately 20 and 50 seconds, respectively, to process the queries on a machine equipped with an AMD Ryzen 5 3600x processor
format Preprint
id arxiv_https___arxiv_org_abs_2309_12071
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Benchmarking quantized LLaMa-based models on the Brazilian Secondary School Exam
Santos, Matheus L. O.
Campelo, Cláudio E. C.
Artificial Intelligence
Computation and Language
53-04
I.2.7; I.2.0
Although Large Language Models (LLMs) represent a revolution in the way we interact with computers, allowing the construction of complex questions and the ability to reason over a sequence of statements, their use is restricted due to the need for dedicated hardware for execution. In this study, we evaluate the performance of LLMs based on the 7 and 13 billion LLaMA models, subjected to a quantization process and run on home hardware. The models considered were Alpaca, Koala, and Vicuna. To evaluate the effectiveness of these models, we developed a database containing 1,006 questions from the ENEM (Brazilian National Secondary School Exam). Our analysis revealed that the best performing models achieved an accuracy of approximately 46% for the original texts of the Portuguese questions and 49% on their English translations. In addition, we evaluated the computational efficiency of the models by measuring the time required for execution. On average, the 7 and 13 billion LLMs took approximately 20 and 50 seconds, respectively, to process the queries on a machine equipped with an AMD Ryzen 5 3600x processor
title Benchmarking quantized LLaMa-based models on the Brazilian Secondary School Exam
topic Artificial Intelligence
Computation and Language
53-04
I.2.7; I.2.0
url https://arxiv.org/abs/2309.12071