Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
개발자를 위한_Large Language Model(LLM) _ 한성민 [Hello ...
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Sungmin Han
July 19, 2023
Technology
100
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
개발자를 위한_Large Language Model(LLM) _ 한성민 [Hello World]
Sungmin Han
July 19, 2023
Transcript
44 slides
Large Language Model(LLM) SungMin Han GDE for ML | GDG
Golang Korea
Speaker (SungMin Han) - MLOps Lead at Riiid - GDE
for ML - GDG Golang Korea Organizer - Python Mentor at F-Lab - Former) Research Engineer at Naver Clova - Former) Software Engineer at 심심이
Agenda • Generative AI • Large Language Model(LLM) • ChatGPT
(and GPT 4) • Instruct GPT • GPT in Go • Appendix
Generative AI
Keywords GPT 4 GPT 3.5 ChatGPT LLaMA Stanford Alpaca T5
Google Bard Megatron-TLG Stable Diffusion MidJourney BingChat DALL·E 2 Microsoft 365 Copilot LaMDA BLOOM
Keywords in 2023 GPT 4 GPT 3.5 ChatGPT LLaMA Stanford
Alpaca T5 Google Bard Megatron-TLG Stable Diffusion MidJourney BingChat DALL·E 2 Microsoft 365 Copilot LaMDA BLOOM
Image Midjourney, NovelAI, Stable Diffusion…
Audio Riffusion MurfAI
Text Google Bard OpenAI ChatGPT
Landscapes https://www.antler.co/blog/generative-ai
Large Language Model (LLM)
(2020) https://www.microsoft.com/en-us/research/blog/turing-nlg-a-17-billion-parameter-language-model-by-microsoft/
2022 https://huggingface.co/blog/large-language-models
ChatGPT
Reinforcement Learning with Human Feedback (RLHF) https://github.com/Hannibal046/Awesome-LLM/blob/main/resources/creepy_llm.jpeg
Intruct GPT (GPT 3.5) ChatGPT (GPT 3.5 turbo) https://matt-rickard.com/gpt-lineage https://lifearchitect.ai/
Instruct GPT: 3 Step Training Method https://openai.com/blog/chatgpt *PPO => Proximal
Policy Optimization Algorithm in the field of Reinforcement Learning
None
None
CTO
None
Manim
Mermaid
Do Anything Now (DAN): ChatGPT
Do Anything Now (DAN): Jailbreak
Prompt Base Awesome ChatGPT Prompt
GPT4: Multi-modal (Image)
LLM 복잡한 문제
한계: 할루시네이션1
None
: regurgitation engine
Instruct GPT
None
LeetCode
None
None
GPT in Go
None
package main import ( "fmt" gpt35 "github.com/AlmazDelDiablo/gpt3-5-turbo-go" ) func main()
{ api_key := "<REDACTED>" instruct := ` 내가 앞으로 음식 재료들을 입력하면, 너가 입력된 재료들을 조합한 음식 키워드를 하나 뽑아줘. 줄 넘김은 하면 안돼 ! 예시 1: INPUT: 시금치, 고추장, 계란, 밥, 콩나물, 고사리 OUTPUT: 비빔밥 예시 2: INPUT: 면, 라면스프, 물 OUTPUT: 라면 시작해볼까?` c := gpt35.NewClient(api_key) fmt.Println("음식 재료를 입력하세요 (쉼표로 구분):") var ingredients string fmt.Scanln(&ingredients)
req := &gpt35.Request{ Model: gpt35.ModelGpt35Turbo, Messages: []*gpt35.Message{ { Role: gpt35.RoleUser,
Content: instruct, }, { Role: gpt35.RoleSystem, Content: "네, 시작해봅시다! 어떤 재료를 사용하실 건가요?", }, { Role: gpt35.RoleUser, Content: ingredients, }, }, } resp, err := c.GetChat(req) if err != nil { panic(err) } fmt.Println("추천 음식:", resp.Choices[0].Message.Content) }
$ go run main.go 음식 재료를 입력하세요 (쉼표로 구분): 시금치,고추장,
나물 추천 음식: 추천하는 음식 키워드는 된장찌개입니다! $ go run main.go 음식 재료를 입력하세요 (쉼표로 구분): 옥수수, 고춧가루, 소금 추천 음식: 옥수수, 고춧가루, 소금으로 만드는 음식은 '옥수수전'입니다. 즐거운 조리되 세요!
Appendix
Appendix: Stanford Alpaca LLaMA GPT 3.5(text-davinci-003) 7B LLM.
None
More Decks by Sungmin Han
See All by Sungmin Han
Gemma for Your Device - IO Extended Inchoen 2025
kennethanceyer
0
64
BigQuery powered by Vertex AI Gemini - 데이터야놀자 2024
kennethanceyer
0
150
Is Go A Good Language to Build Compilers?
kennethanceyer
0
230
CPython 인터프리터 구조 파헤치기 - PyCon Korea 24
kennethanceyer
0
410
개발자 커뮤니티와 함께 성장하기 - DevFest Songdo 2023
kennethanceyer
0
140
DataKorea-Python_Data_생태계_오늘과_내일
kennethanceyer
0
190
Python의 최적화 그리고 C 바인딩 이야기 _ 한성민 [PyCon Korea 2021]
kennethanceyer
0
230
프론트엔드 모던 프레임워크 _ 한성민 [GDG DevFest Seoul 2017]
kennethanceyer
0
140
AI 연구자를 위한 클린코드 _ 한성민 [GDG Devfest Seoul 2019]
kennethanceyer
0
180
Other Decks in Technology
See All in Technology
AI時代における医療情報システムのセキュリティ / Security of Healthcare IT Systems in the AI Era
henryofficial
0
190
gem install とrequire のむこうがわ
ydah
0
220
Claude Codeで新規事業を伸ばせるか? Zennの試行錯誤の記録
wadayusuke
2
240
さようならSSH鍵、こんにちはゼロトラスト ― AIフレンドリーで快適な自宅鯖SSH
atalie2m
14
7.1k
Linuxネットワークスタック進化の軌跡: 過去10年の歩みと最新トレンド
orimanabu
4
750
gradle-best-practices 使ってみた
mikanichinose
0
160
アラートを見直していたら営業組織への理解にちょっとだけ繋がった話
z63d
1
210
高品質と高スピードを支える品質のシフトレフトのアプローチ
goyoki
4
1.6k
Gov-JAWS#9 統合監視機能のマネージドサービス化+AIによる障害時自動調査
fj_yoshimura_kosuke
0
210
【AWS reInvent 2026 関西組 事前勉強会】二度あることは三度ある~調子に乗りそうな3回目の私を戒めたいです~
ttelltte
0
110
E2E Test というハーネス — AI時代の自動テスト民主化
daishukojima
10
5.7k
CloudTrail を推したい
kazzpapa3
1
140
Featured
See All Featured
Primal Persuasion: How to Engage the Brain for Learning That Lasts
tmiket
0
520
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.9k
What’s in a name? Adding method to the madness
productmarketing
PRO
24
4.2k
We Have a Design System, Now What?
morganepeng
55
8.4k
Java REST API Framework Comparison - PWX 2021
mraible
34
9.8k
Un-Boring Meetings
codingconduct
0
500
Exploring anti-patterns in Rails
aemeredith
4
570
Claude Code どこまでも/ Claude Code Everywhere
nwiizo
68
60k
The State of eCommerce SEO: How to Win in Today's Products SERPs - #SEOweek
aleyda
2
12k
Statistics for Hackers
jakevdp
799
230k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
28
3.8k
Believing is Seeing
oripsolob
1
280