[3Win5] Poster session 3

[3Win5-80] An Information System in a Restricted Local Environment Using Small-Scale Language Models

〇Koki Takeishi¹, takayuki shimotomai¹, ryuto ikeuchi¹, shuichiro sakata¹, tomoki takekawa¹, kohei tanaka¹, kei akutsu¹, jukiya noda¹, ryuta tojima¹, Nguyen Chi Linh¹ (1.headwaters)

Keywords:Small Language Model, Fine Tuning, quantization, Vision Language Model

In recent years, numerous large-scale language models have been proposed and released. Meanwhile, smaller-scale language models, which can run in environments with comparatively limited resources, have also been made available and are being utilized. Demand for these models is rising, particularly for security reasons such as the need to avoid sending data outside the system, as well as in scenarios where network connectivity is unstable—like onboard aircraft or during high-speed travel.In this study, we introduce the quantization and fine-tuning techniques required to effectively utilize small-scale language models (SLMs) under such constrained conditions, and present our evaluation of how these approaches impact model accuracy.