KXkonstantinos.xafis
Machine Learning & AIAcademic2025

Local LLM Experiments

Pythonllama-cpp-pythonHugging FaceGGUFscikit-learn

Overview

An investigation of local, quantized instruction-tuned models — no API calls, everything running on the machine. Models: Llama-3.2-3B-Instruct and aya-expanse-8b as GGUF files downloaded from the Hugging Face Hub.

What I built

A CLI with four modes: plain Q&A, varied question sets, alternative responses at different temperature/top-p settings, and embedding-similarity analysis as a bonus exercise. Prompts were tested bilingually (English and Greek) to probe how instruction-tuned models handle code-switching, and an optional --log flag persists every response for review.

Technical highlights

Outcome

Practical working knowledge of running and probing open-weight models locally.