• Home
  • Fine Tuning Open Source LLM

Fine Tuning Open Source LLM

Course Information

  • Sessions 1 day
  • Duration 7.5 hrs
  • Level Beginner
  • Assessment NA

Venue

12 Woodlands Square #07-85/86/87 Woods Square Tower 1, Singapore 737715. 5 mins walk from Woodlands (NS9) MRT station.

The venue is disabled-friendly.

Course Brochure

Download Course Brochure

Prerequisite

This course is for beginners. No prerequisite is required.

Certification

  • Certificate of Achievement from Tertiary Infotech Academy Pte Ltd - Upon meeting at least 75% attendance and passing the assessment(s), participants will receive a Certificate of Achievement from Tertiary Infotech Academy Pte Ltd.

Fine Tuning Open Source LLM

Course Code: C922

4 Review(s) | Add Your Review

Share

What's This Course About

In the era of advanced artificial intelligence, the ability to develop and fine-tune Generative AI (GenAI) models is critical for building high-performance, domain-specific solutions. This course, Fine Tuning Open Source LLM, equips learners with the practical skills and technical knowledge to design, optimize, and evaluate modern AI models using cloud-based tools and frameworks.

Learners will begin by exploring techniques for data ingestion and transformation, including the use of synthetic data to enhance model performance and address data limitations. The course then focuses on building efficient data pipelines and feature engineering workflows, applying optimization strategies to improve model training and scalability.

Participants will gain hands-on experience in fine-tuning pre-trained multi-modal models, leveraging advanced training approaches, loss functions, and parameter optimization techniques to adapt models for specific use cases. Emphasis is placed on improving model accuracy, efficiency, and robustness in real-world deployment scenarios.

In addition, the course addresses critical considerations in modern AI development, including bias detection, explainability, and alignment with performance benchmarks. Learners will evaluate AI solutions to ensure they are reliable, ethical, and aligned with organizational and regulatory expectations.

By the end of the course, learners will be able to design end-to-end GenAI workflows—from data preparation to model fine-tuning and evaluation—enabling them to develop scalable, responsible, and high-performing AI solutions for a wide range of applications.

This course is suitable for data professionals, AI practitioners, and developers seeking to deepen their expertise in Generative AI model development, optimization, and fine-tuning techniques.

This course is part of our AI training in Singapore, where you can browse all our AI courses. See more AI infrastructure courses.

Why Take This Course?

  • Hands-On Learning Learn by doing. Every topic is practised hands-on, so you leave with skills you can use at work straight away.
  • Live Coaching Experienced instructors coach you live, answer your questions and guide you step by step.
  • Free Post-Course Consultation Stuck after class? Message your trainer any time for guidance as you apply what you have learned.
  • Always-Updated Materials Materials are refreshed to stay relevant. Log in to our LMS any time to get the latest version.

Funding Options

No funding is available for this course

For WSQ funding, please checkout the details at WSQ - Generative AI Model Development and Fine Tuning

Course Fee

$350.00 (GST-exclusive)
$381.50 (GST-inclusive)

Course Date

Course Time

* Required Fields

Additional Note

Please bring your own laptop for hands-on training. If you don't have laptop, we can provide spare laptop for training use.

Post-Course Support

  • We provide free consultation related to the subject matter after the course.
  • Please email your queries to enquiry@tertiaryinfotech.com and we will forward your queries to the subject matter experts.

Cancellation & Reschedule Policy

  • You can register your interest without upfront payment. There is no penalty for withdrawal of the course before the class commences.
  • We reserve the right to cancel or re-schedule the course due to unforeseen circumstances. If the course is cancelled, we will refund 100% for any paid amount.
  • Note the venue of the training is subject to changes due to availability of the classroom.

Course Details

Course Details

What You'll Learn

Topic 1: Data Engineering

Topic 2: Exploratory Data Analysis

Topic 3: Modelling

Topic 4: Machine Learning Implementation and Operations

Course Info

Minimum Entry Requirement

Knowledge and Skills

  • Able to operate using computer functions
  • Minimum 3 GCE ‘O’ Levels Passes including English or WPL Level 5 (Average of Reading, Listening, Speaking & Writing Scores)
  • Basic Python programming is recommended

Attitude

  • Positive Learning Attitude
  • Enthusiastic Learner

Experience

  • Minimum of 1 year of working experience.

Target Age Group: 18-65 years old

Minimum Software/Hardware Requirement

Software:

  • A Google account for Google Colab (free T4 GPU runtime) - no local installation needed
  • A free Hugging Face account

Hardware: Windows or Mac laptop with a modern web browser. No local GPU is required.

Job Roles

Job Roles

  • Machine Learning Engineer
  • Data Scientist
  • AI Engineer
  • Data Engineer
  • Cloud Machine Learning Architect
  • ML Operations Engineer
  • AI/ML Consultant
  • Applied Scientist
  • Deep Learning Engineer
  • Cloud Solutions Architect
  • Data Analyst
  • DevOps Engineer (ML-focused)
  • Technical Product Manager (AI/ML)
  • AI Research Engineer
  • Software Engineer (ML Integration)
  • Automation Engineer (AI/ML)

Trainers

Trainers

Dr. Alfred Ang works with open models on his own hardware as well as through cloud APIs, which gives him a grounded view of what it takes to adapt a language model to a specific domain. As founder of Tertiary Courses and Managing Director, CIO, CTO and Chief Instructional Designer of Tertiary Infotech Academy Pte Ltd, he is a full-stack AI developer and Agentic AI solution architect who builds production AI applications using LLM orchestration, RAG pipelines and multi-agent systems on AWS, Kubernetes and DevOps tooling. His certifications include Microsoft Certified Data Scientist (DP-100) and AI Engineer Associate (AI-102), AWS Certified Solutions Architect and AI Practitioner, and he completed a Graduate Diploma in Intelligent Robotics Systems at NUS-ISS. He holds a PhD in Electrical Engineering from NUS, an MSc in Electrical and Electronic Engineering from NTU and a B.Sc (Hons) in Physics from NUS, and has published more than 20 peer-reviewed papers. He is also an IBM certified instructor for the AI Practitioners course. On GitHub, n8n-inventorycontrol runs a local LLM through Ollama to audit stock and compute replenishment, lipsyncdemo runs MuseTalk locally on Apple MPS or CUDA alongside cloud engines, and digitalhuman trains a voice-enabled avatar on an organisation's own content using RAG. These projects have given him practical insight into the trade-offs between prompting, retrieval and adjusting the model itself, and into the data preparation that every approach depends on.

Fine Tuning Open Source LLM is built around the idea that model quality starts with data. Dr. Ang begins with data engineering: ingesting and transforming data, using synthetic data to fill gaps, and building efficient pipelines and feature engineering workflows. The second topic, exploratory data analysis, teaches learners to inspect datasets for quality, balance and bias before any training run, since problems found here are far cheaper to fix than problems found after deployment. The modelling topic covers selecting an open-source base model, preparing training and evaluation sets, applying fine-tuning techniques and comparing the results against the base model and against simpler options such as better prompts or retrieval. The final topic deals with machine learning implementation and operations: deploying the tuned model, monitoring its behaviour, managing versions and controlling cost, which is where his cloud, Kubernetes and DevOps experience comes into play. He is candid about when fine-tuning is worth it and when RAG or prompt design will deliver the same benefit for less effort, a judgement informed by his own builds. He also covers licensing and data privacy considerations when choosing and adapting open-source models, drawing on his Certificate in AI Ethics and Governance (Senior Professional) from NTU. The sessions are hands-on with cloud-based tools and Python notebooks, and learners evaluate their models with clear metrics rather than impressions. As an ACTA-certified trainer and DACE-certified curriculum developer, he paces the technical depth so that data professionals and developers both leave able to repeat the workflow on their own data. To explore his AI engineering projects, view his GitHub portfolio at https://github.com/alfredang and connect with him on LinkedIn at https://www.linkedin.com/in/angchewhoe/

Truman Ng's connection with machine learning dates back to his Electrical Engineering degree at NUS, completed in 2002, where his final year project used fuzzy logic and a neural network to build an AI controller for a DC-DC power converter. In the years that followed he gained over 15 years of project experience in database design, data centre design and enterprise network implementation, and founded Nexplore (S) Pte Ltd to deliver cloud SaaS, IaaS and PaaS solutions along with internet security services. He is an ACTA-certified trainer and holds PMP, Cisco CCNP and CCIP, HP ASE and Huawei HCIE R&S and HCNA Cloud certifications.

In Fine Tuning Open Source LLM, Truman helps learners design, optimise and evaluate domain-specific generative AI models using cloud-based tools and frameworks. The course moves through data engineering, including data ingestion, transformation and the use of synthetic data, into exploratory data analysis and modelling, before closing with machine learning implementation and operations. His background in databases, data centres and cloud infrastructure is especially relevant to the practical side of fine-tuning, from preparing datasets to running training and deployment in the cloud. Participants leave with a clear, hands-on understanding of how to adapt open source LLMs to their own use cases.

Review

Customer Reviews (4)

will recommend Review by Course Participant/Trainee
1. Do you find the course meet your expectation?
2. Do you find the trainer knowledgeable in this subject?
3. How do you find the training environment
. (Posted on 12/30/2021)
might consider Review by Course Participant/Trainee
1. Do you find the course meet your expectation?
2. Do you find the trainer knowledgeable in this subject?
3. How do you find the training environment
. (Posted on 12/30/2021)
Clear explanation Review by Course Participant/Trainee
1. Do you find the course meet your expectation?
2. Do you find the trainer knowledgeable in this subject?
3. How do you find the training environment
Clear explanation (Posted on 12/30/2021)
Might Consider Review by Course Participant/Trainee
1. Do you find the course meet your expectation?
2. Do you find the trainer knowledgeable in this subject?
3. How do you find the training environment
Would be good to signup for Github, docker hub and aws account before we come for the course to avoid obstacle on signup. Forward the required notes for our reading before the course started.

Will be good to go through some Ubuntu basic command needed for the class. Simply typing some of the commands without knowing what is the command is doing. Also can include comment beside each command for reference. Still very blurred after the course. Course schedule too tight from 10 to 5pm. WIll be good to start early maybe before 9am. (Posted on 11/13/2019)

Write Your Own Review

You're reviewing: Fine Tuning Open Source LLM

How do you rate this product? *

  1 star 2 stars 3 stars 4 stars 5 stars
1. Do you find the course meet your expectation?
2. Do you find the trainer knowledgeable in this subject?
3. How do you find the training environment