Rapid Application Development with Large Language Models (LLMs)

Together with hessian.AI and supported by NVIDIA we offer three full day hands-on online expert workshops related to coding and AI. All workshops are part of the NVIDIA Deep Learning Institute and are conducted by certified instructors. Participants of these workshops will learn the fundamentals of deep learning and get practical insights in rapid application development with Large Language Models (LLMs). These workshops are directed at researchers who already have experience with coding, but want to further develop their skills by diving into the vast field of code and AI.

Recent advancements in both the techniques and accessibility of large language models (LLMs) have opened up unprecedented opportunities to help businesses streamline their operations, decrease expenses, and increase productivity at scale. Additionally, enterprises can use LLM-powered apps to provide innovative and improved services to clients or strengthen customer relationships. For example, enterprises could provide customer support via AI companions or use sentiment analysis apps to extract valuable customer insights.

In this course you will gain a strong understanding and practical knowledge of LLM application development by exploring the open-sourced ecosystem including pretrained LLMs, enabling you to get started quickly in developing LLM-based applications.

Your Benefits

By participating in this course, you will:

• Find, pull in, and experiment with the HuggingFace model repository and Transformers API.
• Use encoder models for tasks like semantic analysis, embedding, question-answering, and zero-shot classification.
• Work with conditioned decoder-style models to take in and generate interesting data formats, styles, and modalities.
• Kickstart and guide generative AI solutions for safe, effective, and scalable natural data tasks.
• Explore the use of LangChain for orchestrating data pipelines and environment-enabled agents.

The course covers large language models from beginning to end, starting with fundamentals of transformers, progression into foundational large language models, and finishing in model/agentic orchestration. Each of these sections is designed to equip participants with the knowledge and skills necessary to progress further in developing useful LLM-powered applications.

For active participation in the workshops and to receive a certificate of attendance signed by NVIDIA, you must register with NVIDIA’s Deep Learning Institute. Further details will be provided during registration. Please note that participation is limited to academic students, staff, and researchers. When registering, ensure that your affiliation is clearly indicated through your email address.

Course Outline

Course Introduction

• Overview of course topics and schedule.
• Introduction to HuggingFace and Transformers.
• Discuss how LLMs can enhance enterprise applications.

Transformers and LLMs

• Introduce and motivate the transformer-style architecture from deep learning first principles.
• Understand input-output processing with tokenizers, embeddings, and attention mechanisms.

Task-Specific Pipelines

• Profile encoder models for different NLP tasks where they are most useful.
• Investigate the use of lightweight models for natural language embedding, classification, subsetting, and zero-shot prediction.

Seq2Seq with Decoders

• Introduce GPT-style decoder models for sequence generation and autoregressive tasks.
• Apply encoder-decoder architectures for applications like machine translation and few-shot task completion.

Multimodal Architectures

• Integrate different data modalities (text, images, audio) into LLM workflows.
• Explore multimodal models like CLIP for cross-modal learning, visual language models for image question-answering, and diffusion models for text-guided image generation.

Scaling Text Generation

• Explore LLM inference challenges and deployment strategies, including optimized server deployments.
• Incorporate LLMs into interesting applications that can scale to larger repositories and user bases.

Orchestration and Agentics

• Introduce LangChain for LLM orchestration and agentic workflows.
• Investigate use of agentics and tool-calling for integrating natural language with standard applications and data.

Final Assessment

• Build an LLM-based application integrating text generation, multimodal learning, and orchestration.

Instructor

The instructor is Kajol Raju, AI expert at the AI Service Centre (hessian.AI) specializing in providing AI computing infrastructure through application-oriented AI research.

Language

Workshops will be held in English.

Prerequisites

Introductory deep learning, with comfort with PyTorch and transfer learning preferred. Content covered by DLI’s Getting Started with Deep Learning or Fundamentals of Deep Learning courses, or similar experience is sufficient.

Intermediate Python experience, including object-oriented programming and libraries. Content covered by Python Tutorial (w3schools.com) or similar experience is sufficient.

The tools, libraries and frameworks used are Python, PyTorch, HuggingFace, Transformers, LangChain, and LangGraph.

Regarding hardware requirements you need a Desktop or laptop computer capable of running the latest version of Chrome or Firefox. Each participant will be provided with dedicated access to a fully configured, GPU-accelerated server in the cloud.