Tinh chỉnh LLM : Thực hành RunPod và Multi-GPU

You can systematically learn stock trading automation using Python and the Interactive Brokers API, which holds the top spot in global market share.

You can create a deep learning analysis environment in the cloud using Docker. When Docker images managed by Google, MS, etc. are combined with the cloud, you can work with the latest deep learning analysis methods on your computer.

This course covers the process of automating algorithmic trading in local and cloud environments, and focuses on hands-on practice.

Learn a systematic approach to S&P 500 pair trading with Python. Lay the foundation for an investment strategy that excludes emotions through professional data analysis.

"LoRA-based lightweight fine-tuning: Your first step to creating a customized LLM!" This course is an introductory hands-on lecture designed so that even those encountering LLMs for the first time can easily follow along. We minimize complex theory and guide you step-by-step through the entire process: loading models → applying data → training → comparing results. In a short time, you'll directly experience the flow of cutting-edge lightweight fine-tuning techniques like LoRA and QLoRA, gaining an intuitive understanding of "how LLM fine-tuning works." Even without extensive resources, experience the satisfaction of creating an LLM specialized for your domain!

RAG (Retrieval-Augmented Generation) from theory to the latest multimodal and agent-based RAG! This is a hands-on lecture designed to be understandable even for non-majors. From paper reviews to practical code implementation, it's designed so that even those encountering RAG for the first time can easily follow along.

✅ Out of the entire series (1) ~ (6), (3) CUDA memory hierarchy optimization ✅ NVIDIA GPU + CUDA programming is explained step by step from the basics. ✅ It processes arrays/matrices/image processing/statistical processing/sorting, etc. very quickly with parallel computing in C++/C language.

NLP Conference <Langcon 2024> Presentation Session Video

✅ Of the series (1) to (6), (1) Making a CUDA kernel ✅ NVIDIA GPU + CUDA programming is explained step by step from the basics. ✅ Processes arrays/matrices/image processing/statistical processing/sorting, etc. very quickly with parallel computing in C++/C language.

Explains the basic principles of large language models like ChatGPT, focusing on theory.

✅ This is an introductory lecture (0) that introduces the entire series of lectures (1) to (6). ✅ NVIDIA GPU + CUDA programming is explained step by step from the basics. ✅ It processes arrays/matrices/image processing/statistical processing/sorting, etc. very quickly with parallel computing in C++/C language.