모두를 위한 대규모 언어 모델 LLM Part 3 - 구글 제미나이(Google Gemini) API, OpenAI API와 젬마(Gemma)로 AI 어플리케이션 만들기
AISchool
구글 제미나이(Gemini) 모델의 개념과 Gemini API 활용 방법을 학습하고, Streamlit을 이용해서 다양한 AI 어플리케이션을 만들어보는 강의입니다.
中級以上
openAI API, ChatGPT, gemini
BEST
Large Language Model for Everyone LLM (Large Language Model) Part 1 - Try Fine-Tuning Llama 2
We will learn step by step from the basic concepts of LLM (Large Language Model) to how to fine-tune the Llama 2 model, a high-performance LLM, on the dataset of your choice.
Reviews from Early Learners
What you will learn!
Basic concepts of LLM(Large Language Model)
How to Fine-Tuning the Llama 2 Model, a High-Performance LLM, on My Desired Dataset
How to Fine-Tuning GPT on Your Own Dataset Using the OpenAI API
Various Parameter-Efficient Fine-Tuning (PEFT) techniques
Various prompt engineering techniques to maximize the performance of LLM
LLM in cutting-edge AI technology, from concept to model tuning!
✨ LLM, the flower of cutting-edge AI technology
By properly leveraging Llama2 and the OpenAI API, we can create an LLM that is more powerful than GPT-4, the current strongest LLM, in a narrow range of fields!
- ✅ You can learn step by step from the basic concepts of the latest LLM (Large Language Model) to Llama 2 Fine-Tuning.
- ✅ Learn how to fine-tune Llama 2 on your own dataset, step by step!
Who is this course for?
The latest LLM model
Concepts and principles
Study thoroughly
Those who want to
High-performance open source
LLM Llama 2
In my own dataset
Fine-Tuning
Those who want to
Like PEFT
Latest LLM trends
Those who want to learn
Using the OpenAI API
GPT Fine-Tuning
Learn how
Those who want to
Player lectures ✅
👋 This course requires prior knowledge of Python, deep learning, and natural language processing (NLP) . Be sure to take the courses below first or have equivalent knowledge before taking this course.
Follow-up lecture ✅
Q&A 💬
Q. What is LLM (Large Language Model)?
LLM stands for "Large Language Model," an AI language model trained on large datasets. These models are widely used in natural language processing (NLP) tasks and can perform a variety of tasks, including text generation, classification, translation, question answering, and sentiment analysis.
Typically, LLMs have millions of parameters , enabling the model to learn a wide variety of language patterns and structures. As a result, LLMs can generate remarkably sophisticated and natural-sounding text.
For example, models like the Generative Pre-trained Transformer (GPT) series developed by OpenAI are a prime example of LLM. These models are trained on large text datasets, such as web pages, books, papers, and articles, and can then be applied to a variety of natural language processing tasks.
LLMs are currently being used in many commercial applications and are recognized for their value in diverse fields, including chatbots, search engines, machine translation services, and content recommendation. However, these models may still have limitations in tasks requiring high levels of expertise, and they can also be prone to issues such as generating misinformation, bias, and lack of understanding.
Q. Is player knowledge required?
This course, [Large Language Model for Everyone LLM (Large Language Model) Part 1 - Fine-Tuning Llama 2], covers a detailed explanation and usage of the latest LLM model. Therefore, it assumes a basic understanding of deep learning and natural language processing. If you lack this knowledge, we recommend taking the preceding course, [Introduction to Deep Learning and Natural Language Processing: NLP with TensorFlow - From RNN to BERT] .
📢 Please check before taking the class
- Due to the recording environment , the sound quality of some videos may not be consistent. (Please refer to the lecture [Preview] before taking the course.)
Recommended for
these people
Who is this course right for?
Anyone who wants to learn the concept and use of the Large Language Model (LLM)
Anyone who wants to fine-tune the latest LLM on their own dataset
Those who want to get a job related to deep learning research
Anyone who wants to conduct research related to artificial intelligence/deep learning
Those preparing for graduate school in artificial intelligence (AI)
Need to know before starting?
Experience using Python
Experience of attending the pre-course [NLP with TensorFlow - From RNN to BERT - Introduction to Deep Learning Natural Language Processing with Examples]
9,032
Learners
661
Reviews
350
Answers
4.6
Rating
29
Courses
- AISchool ( http://aischool.ai/ )
- AISchool 유튜브 채널 운영 ( https://www.youtube.com/@aischool_ai )
- 서울대학교 인공지능 및 컴퓨터 비전 연구실 석사
- [솔라리스의 인공지능 연구실] 블로그 운영
- [텐서플로로 배우는 딥러닝] 집필
- S전자 컴퓨터 비전 관련 프로젝트 수행
- 기업대상 [AI 컨설팅 서비스] 제공
- 에이아이스쿨 [TensorFlow와 실습 프로젝트로 배우는 딥러닝-컴퓨터비전 Basic 코스] 강의 진행
Curriculum
All
127 lectures ∙ (30hr 15min)
Course Materials:
Lecture resources
Published:
Last updated:
Reviews
All
83 reviews
4.7
83 reviews
Limited time deal
$66,000.00
25%
$68.20
AISchool's other courses
Check out other courses by the instructor!
Similar courses
Explore other courses in the same field!
