Full Stack LLM Bootcamp (Free)

LLM에 관심있는 분들은 참고하시기 바랍니다.

fullstackdeeplearning에서 올해 초 진행한 LLM Bootcamp 내용입니다. 각 세션마다 유튜브영상과 슬라이드 자료를 공개하고 있으니 참고하시기 바랍니다.


1. Learn to Spell: Prompt Engineering

-- https://fullstackdeeplearning.com/llm-bootcamp/spring-2023/prompt-engineering/

  • High-level intuitions for prompting

  • Tips and tricks for effective prompting: decomposition/chain-of-thought, self-criticism, ensembling

  • Gotchas: "few-shot learning" and tokenization


2. LLMOps

-- https://fullstackdeeplearning.com/llm-bootcamp/spring-2023/llmops/

  • Comparing and evaluating open source and proprietary models

  • Iteration and prompt management

  • Applying test-driven-development and continuous integration to LLMs


3. UX for Language User Interfaces

-- https://fullstackdeeplearning.com/llm-bootcamp/spring-2023/ux-for-luis/

  • General principles for user-centered design

  • Emerging patterns in UX design for LUIs

  • UX case studies: GitHub Copilot and Bing Chat


4. Augmented Language Models

-- https://fullstackdeeplearning.com/llm-bootcamp/spring-2023/augmented-language-models/

  • Augmenting language model inputs with external knowledge

  • Vector indices and embedding management systems

  • Augmenting language model outputs with external tools


5. Launch an LLM App in One Hour

-- https://fullstackdeeplearning.com/llm-bootcamp/spring-2023/launch-an-llm-app-in-one-hour/

  • Why is now the right time to build?

  • Techniques and tools for the tinkering and discovery phase: ChatGPT, LangChain, Colab

  • A simple stack for quickly launching augmented LLM applications


6. LLM Foundations

-- https://fullstackdeeplearning.com/llm-bootcamp/spring-2023/llm-foundations/

  • Speed-run of ML fundamentals

  • The Transformer architecture

  • Notable LLMs and their datasets


7. Project Walkthrough: askFSDL

-- https://fullstackdeeplearning.com/llm-bootcamp/spring-2023/askfsdl-walkthrough/

  • Walkthrough of a GitHub repo for sourced Q&A with LLMs

  • Try it out via a bot in our Discord

  • Python project tooling, ETL/data processing, deployment on Modal, and monitoring with Gantry


8. What's Next?

-- https://fullstackdeeplearning.com/llm-bootcamp/spring-2023/whats-next/

  • Can we build general purpose robots using multimodal models?

  • Will models get bigger or smaller? Are we running out of data?

  • How close are we to AGI? Can we make it safe?


9. Reza Shabani: How To Train Your Own LLM

-- https://fullstackdeeplearning.com/llm-bootcamp/spring-2023/shabani-train-your-own/

  • The "Modern LLM Stack": Databricks, Hugging Face, MosaicML, and more

  • The importance of knowing your data and designing preprocessing carefully

  • The features of a good LLM engineer

  • By Reza Shabani, who trained Replit's code completion model, Ghostwriter.


10. Harrison Chase: Agents

-- https://fullstackdeeplearning.com/llm-bootcamp/spring-2023/chase-agents/

  • The "agent" design pattern: tool use, memory, reflection, and goals

  • Challenges facing agents in production: controlling tool use, parsing outputs, handling large contexts, and more

  • Exciting research projects with agents: AutoGPT, BabyAGI, CAMEL, and Generative Agents

  • By Harrison Chase, co-creator of LangChain


11. Fireside Chat with Peter Welinder

-- https://fullstackdeeplearning.com/llm-bootcamp/spring-2023/welinder-fireside-chat/

  • With Peter Welinder, VP of Product & Partnerships at OpenAI

  • How OpenAI converged on LLMs

  • Learnings and surprises from releasing ChatGPT

The Full Stack - Learn to Spell: Prompt Engineering

Fullstackdeeplearning

The Full Stack - Learn to Spell: Prompt Engineering

다음 내용이 궁금하다면?

또는

이미 회원이신가요?

2023년 11월 8일 오전 7:57

 • 

저장 24조회 2,827

댓글 0

    함께 읽은 게시물


    면접 탈락 이유 복기

    

    ... 더 보기

    커서 AI를 슬랙과 연결하면 생기는 일

    ... 더 보기

    정직한 경험 소개

    

    ... 더 보기

     • 

    저장 3 • 조회 683


    회사가 직원들에게 요구하는 것 중 하나가 ‘애사심’이다. 애사심은 분명히 숭고한 가치이지만, 그렇다고 강제로 요구한다고 생기는 것은 아니다. 직원들이 먼저 회사에 자부심을 갖도록 환경을 조성해야 자연스럽게 애사심도 고취될 수 있다.

    ... 더 보기

    직원들 자부심 챙기면 애사심은 절로 나온다

    서울경제

    직원들 자부심 챙기면 애사심은 절로 나온다

    조회 226


    [ 좋은 리더십은 좋은 팔로어십으로부터 ]

    01. 흔히 '리더십은 이끄는 것이고 팔로어십은 따르는 것'이라고 생각하기 쉽습니다. 뭐 구조만 두고 보면 아주 틀린 말은 아닙니다. 하지만 이를 마치 작용과 반작용처럼 생각하면 그때부터는 조직 내에서 큰 오해가 생길 수 있죠. 때문에 이 둘 사이의 방점은 '상호보완적'이라는데 찍혀야 함이 분명합니다. 02. 우리 주변에서 리더가 된 사람들 중 이런 유형이 있습니다. 일을 할 때 다른 사람들보다 자신의 의견을 더 잘 메이킹하고, 상위 리더의 지시를 누구보다 빠르게 잘 따르며, 피플 매니징에 대한 의욕이 높은... 더 보기

     • 

    저장 34 • 조회 2,673