PHAROS Training Series - Course 12 "Compute-Efficient Methods for Large Language Models"

Friday 17 Jul 2026, 11:00 → 14:00 Europe/Athens

PHAROS AI Factory announces the 12th Course of its Training Series, under the title "Compute-Efficient Methods for Large Language Models", under the topic LLMs, organised in collaboration with Pharos-CY, held online via Zoom.  

Date: July 17th, 2026, at 11:00 EEST 

Location: Online via Zoom

Presentation Language: English

Audience: Data Scientists, ML Engineers, AI Engineers, Academic Researchers

Level: Intermediate

Prerequisites: Machine Learning, Python

Learning Objectives: 

By the end of the seminar, participants will be able to:

• Identify key efficiency methods for training, fine-tuning, and inference.
• Describe how LoRA enables parameter-efficient fine-tuning of LLMs.
• Apply a basic Hugging Face workflow for dataset preparation, training, evaluation, and inference.
• Compare trade-offs between model performance, cost, memory use, and deployment efficiency.

Instructors’ Short Bios:

• Professor Constantine Dovrolis is Director of the Computation-based Science and Technology Research Center (CaSToRC) at The Cyprus Institute and, starting in September 2026, XM Chair in Artificial Intelligence at the University of Cyprus. He served on the faculty of the School of Computer Science at the Georgia Institute of Technology from 2002 to 2025 and is an ACM Distinguished Member. His research spans machine learning, network science, and data-driven modeling, with a recent focus on neuro-inspired artificial intelligence. A central question in his work is how principles underlying the structure and function of brain networks—such as sparsity, modularity, plasticity, and hierarchy—can guide the design of more adaptive, efficient, and interpretable learning systems. His work has appeared at venues including ICML, NeurIPS, CVPR, and TMLR. He also collaborates broadly across neuroscience, biology, medicine, and climate science, with funding from NSF, NIH, DOE, DARPA, Horizon Europe, and Cyprus’ RIF.

 

• Dr. Nikos Bakas is a Senior Data Scientist at GRNET with a broad background in Artificial Intelligence. He has authored numerous publications across AI thematic areas including Machine Learning, Numerical Methods, Optimization, and Large Language Models. He has served as principal investigator, researcher, and coordinator in multiple projects at research centers and universities. Dr. Bakas holds a Ph.D. from the National Technical University of Athens and has long-standing teaching experience. He also brings extensive programming expertise in a wide range of languages and frameworks, and the training seminars he has organized have reached a broad community of engineers.

 

• Roman Dolgopolyi is an Artificial Intelligence Developer at GRNET. He has extensive experience in training, fine-tuning, and benchmarking both Large Language Models and Vision-Language Models. His previous work has been recognized in reputable academic journals and venues, including Springer Nature publications and the EMCIS Conference.

 

Note: Please enter your institutional/corporate email when registering.

 

Form of Withdrawal of Consent for photos,videos.pdf

Form of Withdrawal of Consent, Registration.pdf

Read the Privacy Statement Here.pdf

11:00 → 12:00 Efficient training, fine-tuning and inference of large-scale ML models

This presentation reviews the main algorithmic and systems-level ideas for making large-scale generative AI more efficient across the full model lifecycle: pre-training, fine-tuning, and inference. It introduces the computational challenges created by scaling laws, model size, memory footprint, and long-context generation, then surveys model-centric approaches such as quantization, pruning, low-rank approximation, knowledge distillation, mixed-precision training, sparse initialization, and parameter-efficient fine-tuning methods including adapters, prompt tuning, and LoRA-style techniques. The presentation also covers inference-time acceleration, including speculative decoding, KV-cache optimization, efficient attention variants, mixture-of-experts architectures, and long-context methods. The talk is intended for audiences interested in deploying, adapting, or studying large-scale ML models under realistic compute and cost constraints.

Speaker: Constantine Dovrolis (The Cyprus Institute)

Efficient-LLM-training.pdf

12:00 → 13:00 Fine-Tuning Transformers for Medical Reasoning with LoRA and Hugging Face Trainer

This talk demonstrates a practical, end-to-end notebook for fine-tuning a reasoning-capable transformer model for medical question answering. Participants will learn how to use Hugging Face Datasets and Trainer to handle the training workflow, from loading and cleaning data to tokenization, checkpointing, evaluation, and inference. The session demonstrates parameter-efficient fine-tuning with LoRA, showing how a 3B-class Mistral reasoning model can be adapted on a single 16 GB GPU by training only small adapter weights instead of the full model. The notebook combines MedReason and medical-o1 reasoning datasets into a unified question, chain-of-thought, and answer format, then trains and evaluates the model on a small demo subset. By the end, attendees will understand the key engineering choices behind efficient LLM fine-tuning and see a side-by-side comparison of base and fine-tuned model behavior on medical reasoning tasks, including practical notes on GPU setup, mixed precision, and resource cleanup for reproducible classroom demos.

Speaker: Roman Dolgopolyi (GRNET)

Fine-Tuning Transformers for Medical Reasoning with LoRA and Hugging Face Trainer

13:00 → 13:10 Break

13:10 → 13:40 Introduction to Fully Sharded Data Parallel (FSDP)

Speakers: Nikos Bakas (GRNET) , Roman Dolgopolyi (GRNET)

FSDP_presentation.pdf

13:40 → 14:00 The Pharos training platform

In this talk, we will briefly navigate you through our recently launched Pharos Training Platform. You may navigate various talks and hands-on material on Machine Learning, Deep Learning, NLP, LLMs, Computer Vision, Advanced GenAI, HPC, AI Ethics, AI4Health, AI4Sustainability, and AI4LanguageCulture: https://www.pharos-aifactory.eu/pharos-training-platform/

Speaker: Margarita Markoulatou (GRNET)

PharosTrainingPlatform.pdf