강의

멘토링

로드맵

AI Development

/

Deep Learning & Machine Learning

LLM Finetuning : RunPod and Multi-GPU Practice

Packed with LLM Fine-Tuning Know-how, learned from Silicon Valley LLM Project Practitioners.

(4.8) 5 reviews

33 learners

  • danielyouk
multi-gpu
환경구축
ai개발
LLM
RunPod
openAI API
GPU
Parallel Processing

What you will learn!

  • LLM Fine Tuning

  • Multi GPUs

  • OpenAI API

  • Ollama

  • Hugging Face

The Core of AI Customization
Fine Tuning & Multi-GPU

No more same old AI!
Sharing practical AI customization know-how from a Silicon Valley LLM project lead .

API, fine tuning, and multi-GPU all at once

This course covers the core skills required for practical LLM development, including API utilization, dataset creation, fine-tuning, and multi-GPU setup.

Learn how to use RunPod quickly and easily

RunPod, the key to leveraging multi-GPUs! Efficiently build a multi-GPU environment without wasting time by selecting only the necessary sections from the official documentation.

Increasing the efficiency of AI development
GPU solution, RunPod !



RunPod is a service that allows you to rent virtual GPUs in the cloud to train and deploy AI models . It easily builds a multi-GPU environment for efficient, large-scale training and inference. With hourly billing, you can use only as much as you need, resulting in significant cost savings. Furthermore, you can immediately leverage the latest GPUs without complex infrastructure, maximizing AI performance.

Learn about these things

Multi-GPU Fine-Tuning: Creating the Optimal LLM Training Environment

Learn how to efficiently conduct LLM training without hardware limitations using multi-GPUs. This guide details how to build a multi-GPU environment using the RunPod service and connect to the Pod from your local environment via SSH.


Building Your Own LLM: Customizing AI Models with Fine-Tuning

Now, build your own AI as smart as ChatGPT! In this course, you'll learn how to fine-tune an AI model that converts Korean input into Shakespearean English .

Leveraging the OpenAI API: Building the Dataset Required for Model Training

By leveraging the OpenAI API, you can overcome data shortage issues and efficiently secure high-quality data needed for model training.

from openai import OpenAI client = OpenAI() completion = client.chat.completions.create( model= "gpt-4o" , messages=[ { "role" : "developer" , "content" : "You are a helpful assistant." }, { "role" : "user" , "content" : "Translate the following English text into a Shakespearean style." } ] ) print (completion.choices[ 0 ].message)


AI Development Hands-on: Fine-Tuning Your LLM with the Latest Technology Stack

From generating data with the OpenAI API, downloading LLM from HuggingFace, running models with Ollama, and optimizing with RunPod GPU, you'll experience the latest AI technology stack all at once and master the practical workflow of LLM fine-tuning.


Things to note before taking the course

Practice environment

  • Operating System and Version (OS): All OS are supported, including Windows, macOS, and Linux.

  • Tools used: Visual Studio Code, Ollama, Hugging Face API, OpenAI API, llama.cpp

  • PC specifications: PC with basic specifications capable of Internet access

Learning Materials

  • Learning material formats provided: Jupyter Notebook, lecture script

  • All lecture content is provided as text files. After class, you can use the search function to quickly find the section you need.

Player Knowledge and Precautions

  • No prior knowledge is required.

  • For those who are not familiar with the usage of the hugging face API covered in the lecture, it may feel a little difficult, but it is something that can be easily solved by following the lecture content and searching for chatgpt.

  • We encourage you to utilize the bulletin board. We'll provide in-depth, detailed answers to any questions you have about class-related topics.

Recommended for
these people

Who is this course right for?

  • Developer wanting to build their own Chat model

  • Everyone who wants to learn Multi GPU model training

Need to know before starting?

  • (Optional) Problem-solving ability via Chatgpt search

Hello
This is

611

Learners

63

Reviews

73

Answers

4.8

Rating

7

Courses

  • LLM 기반 AI 기업에서 Pod Lead로 활동

  • 서울대학교 기계항공 공학부 졸업

  • 유럽 소재 대학원에서 기계항공공학 석사

  • 독일 소재 공학 연구기관에서 박사 과정 연구 수행

  • 유럽 대형 에너지 기업에서 Senior Data Scientist 경험

  • 영국 소재 에너지 컨설팅 기업에서 Senior Consultant 활동

  • Databricks 기반 데이터 엔지니어링 프로젝트 수행

  • Kaggle 주식 거래 AI 대회 Top 3% 성과

  • AI Agent 개발팀장으로 현재 활동 중

Curriculum

All

20 lectures ∙ (3hr 26min)

Course Materials:

Lecture resources
Published: 
Last updated: 

Reviews

All

5 reviews

4.8

5 reviews

  • 배소정님의 프로필 이미지
    배소정

    Reviews 3

    Average Rating 5.0

    5

    30% enrolled

    • brand13님의 프로필 이미지
      brand13

      Reviews 9

      Average Rating 5.0

      5

      30% enrolled

      • 류하경님의 프로필 이미지
        류하경

        Reviews 2

        Average Rating 5.0

        5

        65% enrolled

        • handover.oh님의 프로필 이미지
          handover.oh

          Reviews 1

          Average Rating 4.0

          4

          100% enrolled

          • hakjuknu님의 프로필 이미지
            hakjuknu

            Reviews 155

            Average Rating 5.0

            5

            30% enrolled

            great!

            Limited time deal

            $45,370.00

            25%

            $47.30

            danielyouk's other courses

            Check out other courses by the instructor!

            Similar courses

            Explore other courses in the same field!