Saved in:
Bibliographic Details
Main Authors: Venkatesh, Vinay, Kamanuru, Vamsidhar R, Kumar, Lav, Kothari, Nikita
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.03284
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911191052320768
author Venkatesh, Vinay
Kamanuru, Vamsidhar R
Kumar, Lav
Kothari, Nikita
author_facet Venkatesh, Vinay
Kamanuru, Vamsidhar R
Kumar, Lav
Kothari, Nikita
contents This paper proposes Edge-FIT (Federated Instruction Tuning on the Edge), a scalable framework for Federated Instruction Tuning (FIT) of Large Language Models (LLMs). Traditional Federated Learning (TFL) methods, like FedAvg, fail when confronted with the massive parameter size of LLMs [3], [6]. Our Edge-FIT framework combines federated learning with 4-bit Quantized Low-Rank Adaptation (QLORA), mitigating the core issues of communication and computational overhead. We demonstrate this by filtering the general-purpose Databricks Dolly 15k dataset for the IoT domain. Experimental results show the Edge-FIT tuned Llama 2(7B) achieves an F1-Score of 0.89. We also demonstrate a viable trade-off using the 3.8B Phi-3-mini model, validating Edge-FIT as a scalable framework for decentralized LLM deployment on home compute gateways.
format Preprint
id arxiv_https___arxiv_org_abs_2510_03284
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Edge-FIT: Federated Instruction Tuning of Quantized LLMs for Privacy-Preserving Smart Home Environments
Venkatesh, Vinay
Kamanuru, Vamsidhar R
Kumar, Lav
Kothari, Nikita
Machine Learning
Artificial Intelligence
This paper proposes Edge-FIT (Federated Instruction Tuning on the Edge), a scalable framework for Federated Instruction Tuning (FIT) of Large Language Models (LLMs). Traditional Federated Learning (TFL) methods, like FedAvg, fail when confronted with the massive parameter size of LLMs [3], [6]. Our Edge-FIT framework combines federated learning with 4-bit Quantized Low-Rank Adaptation (QLORA), mitigating the core issues of communication and computational overhead. We demonstrate this by filtering the general-purpose Databricks Dolly 15k dataset for the IoT domain. Experimental results show the Edge-FIT tuned Llama 2(7B) achieves an F1-Score of 0.89. We also demonstrate a viable trade-off using the 3.8B Phi-3-mini model, validating Edge-FIT as a scalable framework for decentralized LLM deployment on home compute gateways.
title Edge-FIT: Federated Instruction Tuning of Quantized LLMs for Privacy-Preserving Smart Home Environments
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2510.03284