Local LLM runner (GPU version)
Year of publication
2024
Authors
Merilehto, Juhani
Abstract
Local LLM Runner is a Python-based tool that enables local execution of Large Language Models (LLMs) with GPU acceleration. It was developed for the Strategic Exercise Information and Research unit in Likes Institute, at JAMK University of Applied Sciences. The tool provides a simple command-line interface for interacting with various GGUF-format language models, with specific optimization for the OpenHermes 2.5 model.
Show moreOrganizations and authors
JAMK University of Applied Sciences
Merilehto Juhani 
Publication type
Publication format
Information and communication technology application
Audience
Professional
MINEDU's publication type classification code
I2 ICT applications
Publication channel information
Publisher
Jyväskylän ammattikorkeakoulu
Open access
Open access in the publisher’s service
Yes
Open access of publication channel
Fully open publication channel
Self-archived
No
Other information
Fields of science
Computer and information sciences
Keywords
[object Object],[object Object],[object Object],[object Object],[object Object]
Publication country
Finland
Internationality of the publisher
Domestic
Language
English
International co-publication
No
Co-publication with a company
No
The publication is included in the Ministry of Education and Culture’s Publication data collection
Yes