I am a Google Developer Expert in Machine Learning and I deliver technical talks across India and internationally. These are my ready-made talks sorted according to their level. Please note that none of my talks are actually for absolute beginners and basic Python knowledge, basic understanding of machine learning concepts, and some experience with PyTorch is a prerequisite. You can get in touch with me if you want a custom-made talk for your event.

Beginner

Building Multimodal Search and RAG with Gemini Vision model

Build smarter search and RAG applications for multimodal retrieval and generation.

• Learn how multimodality works by implementing contrastive learning, and see how it can be used to build modality-independent embeddings for seamless any-to-any retrieval.
• Build multimodal RAG systems that retrieve multimodal context and reason over it to generate more relevant answers.
• Implement industry applications of multimodal search and build multi-vector recommender systems.

Intermediate

QLoRA Finetuning & DPO Aligning Google's Gemma with Hugging Face

We discuss Supervised Finetuning and a powerful alignment technique called Direct Preference Optimisation (DPO) which was used to train Zephyr (https://arxiv.org/abs/2310.16944) and is rapidly becoming the de facto method to boost the performance of open chat models. By the end of this session, attendees will:

• Understand the steps involved in fine-tuning LLMs for chat applications.
• Learn the theory behind Direct Preference Optimisation and how to apply it in practice with the Hugging Face TRL library.
• Know what metrics to consider when evaluating chat models.