NVIDIA Workshop: Rapid Application Development Using Large Language Models

AI Lab in collaboration with NVIDIA Deep Learning Institute (DLI) invite you to attend the Artificial Intelligence online instructor-led hands-on NVIDIA workshop: " Rapid Application Development Using LArge Language Models" which will be delivered on:Saturday December 12, 2025 from 9:00 am till 5:00 pm(UTC+3).

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.

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.

By participating in this workshop, you’ll:

• Find, pull in, and experiment with the HuggingFace model repository and the associated Transformers API.
• Use encoder models for tasks like semantic analysis, embedding, question-answering, and zero-shot classification.
• Use decoder models to generate sequences like code, unbounded answers, and conversations.
• Use state management and composition techniques to guide LLMs for safe, effective, and accurate conversation

Topics Covered

The workshop covers large language models from beginning to end, starting with fundamentals of transformers, progression into foundational large language models, and finishing in model/agent 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.

Course Outline

• Introduction to HuggingFace
• The Deep Learning Intuitions of LLMs
• Wrapping Models Into Task-Specific Pipelines
• Encoder-Decoders for Autoregressive Seq2Seq
• Cross-Attention for Multi-Modal Reasoning
• Scaling to Large Foundational Decoder Models
• Introduction to Stateful Agentic Systems
• Final Assessment: Building An Agent

Workshop Prerequisites:

Python programming experience, basic understanding of neural networks, and a fundamental understanding of a deep learning framework such as TensorFlow or PyTorch

Tools, libraries, frameworks used:

Python, PyTorch, HuggingFace, Transformers, LangChain, and LlamaIndex

Hardware Requirements:

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.

Assessment Type:

Skills-based coding assessments evaluate students’ ability to build an LLM application.

Certificate:

Upon successful completion of the assessment, participants will receive an NVIDIA DLI certificate to recognize their subject matter competency and support professional career growth.

Workshop Setup Instructions:

1. Create an NVIDIA Developer account at http://courses.nvidia.com/join.

2. Make sure that WebSockets works for you:

• Test your laptop at http://websocketstest.com

• Under ENVIRONMENT, confirm that “WebSockets” is checked yes.

• Under WEBSOCKETS (PORT 80), confirm that “Data Receive,” “Send,” and “Echo Test” are checked yes.

3. If there are issues with WebSockets, try updating your browser. We recommend Chrome, Firefox, or Safari for an optimal performance.

4. Please test your system / audio by clicking on the following link: https://smart.newrow.com/room/testPage. We highly recommend the use of headsets to get the best audio quality possible and to limit background noise and feedback. If you experience webcam or audio problems, go to: https://support.newrow.com/en/article/is-your-webcam-or-microphone-blocked-by-browser for resolution.

Systems problems will likely either require upgrading your browser or pertain to problems with your internet connection. You will be responsible for resolving these issues.

5. Watch for an email with login details that will include the classroom name, URL, and password.

6. 15 minutes prior to your event time, please visit the classroom URL that will be sent to your email and enter your name and password.

Students may see a message like the following if they connect to the classroom before the instructor arrives – “Classroom unavailable. Waiting for the host to start the session…”. Attendees will just need to wait until the instructor arrives into the classroom.

Instructor:

Dr. Manal Jalloul is a lecturer and researcher at the American University of Beirut. Her research interests lie in the fields of digital image and video processing, 3D printing, parallel computing, and artificial intelligence. She has several peer-reviewed publications in international journals and conferences. She is also a research consultant for emerging tech startups. She is a certified instructor and University ambassador at Nvidia’s Deep Learning Institute (DLI). She is also the co-founder of AI-Lab, which is the certified partner of NVIDIA in EMEA. AI Lab aims to provide specialized hands-on trainings and consulting services in the fields of Artificial Intelligence, Accelerated Computing, and Data Analytics to the industry in the region.

Email: manal.jalloul@ailabsolutions.com

LinkedIn: Dr. Manal Jalloul

This workshop is brought to you by:

www.ailabsolutions.com