Patrick Haralabidis
Google Developer Expert (GDE) AI - Machine Learning | GCP Champion Innovator in AI/ML | Melbourne TensorFlow User Group Organiser | Engineering Chapter Lead @Flybuys
Melbourne, Australia
Actions
Patrick is a Google Developer Expert (GDE) in AI and Machine Learning, a Cloud Champion Innovator, and the Melbourne TensorFlow User Group organiser.
He currently leads the ML and Software Engineering Chapter at Flybuys, where he leverages his extensive experience spanning backend, mobile, cloud, and AI technologies. Patrick excels at developing solutions in emerging tech fields, focusing on rapid prototyping and agile development methodologies.
A passionate advocate for knowledge sharing, Patrick is a skilled technical trainer with a proven track record of delivering engaging and informative sessions. He is deeply committed to building technical communities, fostering shared learning, and pushing the boundaries of transformative technologies.
Links
Awards
Area of Expertise
Topics
Unlocking Specialized AI: Hands-on Fine-Tuning with Gemma 2
Large Language Models (LLMs) like Gemma 2 possess remarkable capabilities, but their true potential lies in their adaptability.
In this talk, we'll embark on a journey into the heart of fine-tuning, the technique that transforms these general-purpose language powerhouses into specialized task masters.
We'll demystify the fine-tuning process, walking you through practical examples using Hugging Face and LoRA to adapt Gemma 2 for your projects. Whether you're interested in chatbots, text summarization, or sentiment analysis, you'll leave this session equipped with the knowledge and skills to unlock the full potential of LLMs.
Key Takeaways:
Gain a deep understanding of what fine-tuning is and why it's crucial for LLM applications.
Learn about the various types of fine-tuning and how to choose the right one for your project.
Follow a step-by-step walkthrough of fine-tuning Gemma 2, from data preparation to deployment.
Discover best practices for fine-tuning, ensuring optimal performance and efficiency.
Be empowered to harness the power of LLMs to create innovative and impactful solutions.
Unlock the Power of Gemini Function Calling: A Practical Introduction
Delve into Gemini Function Calling, a cutting-edge feature that seamlessly empowers language models to interact with external data sources and APIs.
This talk will provide a hands-on exploration of how to leverage Gemini Function Calling to enhance the capabilities of your AI applications. We'll cover the fundamentals, demonstrate real-world use cases, and equip you with the knowledge to integrate this powerful tool into your projects.
Key Takeaways:
- Understand the core concepts of Gemini Function Calling
- Learn how to define and utilize custom functions within the Gemini framework
- Discover practical examples of how to call external APIs and integrate the results into language model outputs
- Gain insights into best practices for optimizing and troubleshooting your Gemini Function Calling implementations
This talk is ideal for developers, data scientists, and anyone interested in expanding the capabilities of their AI applications.
Demystifying Generative AI: From LLMs to Real World Applications
Generative AI has emerged, promising to revolutionize how we create and interact with technology. Large Language Models (LLMs) like Gemini have captured the imagination, generating human-like text, code, and creative content. But beyond the hype, developers must grasp this transformative technology's core concepts, tools, and ethical implications.
This talk is dedicated to demystifying generative AI, providing a clear and accessible overview for developers of all levels. We'll start by exploring the foundations: what LLMs are, how they work, and how they differ from traditional AI models. We'll delve into popular generative AI models like Transformers, GANs, and VAEs, highlighting their unique strengths and applications, ensuring you feel reassured and confident in your understanding.
Next, we'll dive into the practical side, showcasing essential tools and frameworks for working with LLMs, like Hugging Face Transformers, LangChain, Ollama and Gemini's API. We will illustrate how to navigate, select and harness these tools to build real-world applications.
Finally, we'll address the ethical considerations surrounding generative AI, discussing bias and misinformation. We'll emphasize the importance of responsible AI development and provide practical tips for building fair and transparent AI systems.
Takeaways for the Audience:
Gain a solid understanding of generative AI, LLMs, and related technologies.
Discover practical tools, frameworks and techniques for building real-world applications.
Learn how to address the ethical challenges of generative AI responsibly.
Be inspired to explore the vast potential of generative AI in their projects.
Patrick Haralabidis
Google Developer Expert (GDE) AI - Machine Learning | GCP Champion Innovator in AI/ML | Melbourne TensorFlow User Group Organiser | Engineering Chapter Lead @Flybuys
Melbourne, Australia
Links
Actions
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top