Mastering LLMs For Developers & Data Scientists
6 Weeks
·Cohort-based Course
An online course for everything LLMs.
Mastering LLMs For Developers & Data Scientists
6 Weeks
·Cohort-based Course
An online course for everything LLMs.
Course overview
Build skills to be effective with LLMs
This started as an LLM fine-tuning course. It organically grew into a learning event with world-class speakers on a broad range of LLM topics. The original fine-tuning course is still here as a series of workshops. But there are now many self-contained talks and office hours from experts on many Generative AI topics.
All materials + recordings will be available to participants who enroll. There are 11 talks and 4 workshops (and growing) in addition to office hours.
Conference Talks
------------------------------
Jeremy Howard: Co-Founder Answer.AI & Fast.AI
- Build Applications For LLMs in Python
Sophia Yang: Head of Developer Relations, Mistral AI
- Best Practices For Fine Tuning Mistral
Simon Willison: Creator of Datasette, co-creator of Django, PSF Board Member
- Language models on the command-line
JJ Allaire: CEO, Posit (formerly RStudio) & Researcher for the UK AI Safety Institute
- Inspect, An OSS framework for LLM evals
Wing Lian: Creator of Axolotl library for LLM fine-tuning
- Fine-Tuning w/Axolotl
Mark Saroufim and Jane Xu: PyTorch developers @ Meta
- Slaying OOMs with PyTorch FSDP and torchao
Jason Liu: Creator of Instructor
- Systematically improving RAG applications
Paige Bailey: DevRel Lead, GenAI, Google
- When to Fine-Tune?
Emmanuel Ameisen: Research Engineer, Anthropic
- Why Fine-Tuning is Dead
Hailey Schoelkopf: research scientist, Eleuther AI, maintainer, LM Evaluation Harness
- A Deep Dive on LLM Evaluation
Johno Whitaker: R&D at AnswerAI
- Fine-Tuning Napkin Math
John Berryman: Author of O'Reilly Book Prompt Engineering for LLMs
- Prompt Eng Best Practices
Ben Clavié: R&D at AnswerAI
- Beyond the Basics of RAG
Abhishek Thakur leads AutoTrain at HuggingFace
- Train (almost) any llm model using 🤗 Autotrain
Kyle Corbitt is currently building OpenPipe
- From prompt to model: fine-tuning when you've already deployed LLMs in prod
Ankur Goyal: CEO and Founder at Braintrust
- LLM Eval For Text2SQL
Freddy Boulton: Software Engineer at 🤗
- Let's Go, Gradio!
Jo Bergum: Distinguished Engineer at Vespa
- Back to basics for RAG
Fine-Tuning Course
---------------------------
Run an end-to-end LLM fine-tuning project with modern tools and best practices. Four workshops guide you through productionizing LLMs, including evals, fine-tuning and serving.
Workshop 1: Determine when (and when not) to fine-tune an LLM
Workshop 2: Train your first fine-tuned LLM with Axolotl
Workshop 3: Set up instrumentation and evaluation to incrementally improve your model
Workshop 4: Deploy Your Model
This is accompanied by 5+ hours of office hours. Lectures explain the why and demonstrate the how for all the key pieces in LLM fine-tuning. Your hands-on-experience in the course project will ensure your ready to apply your new skills in real business scenarios.
The Fine-Tuning course has these guest speakers:
- Shreya Shankar: LLMOps and LLM Evaluations researcher
- Zach Mueller: Lead maintainer of HuggingFace accelerate
- Bryan Bischof: Director of AI Engineering at Hex
- Charles Frye: AI Engineer at Modal Labs
- Eugene Yan: Senior Applied Scientist @ Amazon
- Harrison Chase: CEO of LangChain
- Travis Addair: Co-Founder & CTO of Predibase
- Joe Hoover: Lead ML Engineer at Replicate
FAQ:
-------
Q: It says this course already started. Should I still Enroll?
A: Yes. Everything is recorded, so you can watch videos for any events that have happened so far, join for live events moving forward, and even learn from talks long after the conference is over.
Q: Will there be a future cohort?
A: No. We were fortunate to have so many world-class speakers. We don't think this can be replicated, so it is now a one-time-only event with all recordings available.
Q: Are you still giving out free compute credits?
A: No. Students who enrolled after 5/29/2024 are not eligible for compute credits. You will still get access to the lectures and recordings. EXCEPTION: if you enroll in the course by 6/10/2024 and use Modal by 6/11/2024, they will give you $1,000 in compute credits.
Who Is It For?
01
Data scientists looking to repurpose skills from conventional ML into LLMs and generative AI
02
Software engineers with Python experience looking to add the newest and most important tools in tech
03
Programmers who have called LLM APIs that now want to take their skills to the next level by building and deploying fine-tuned LLMs
What you’ll get out of this conference
Connect With A Large Community Of AI Practitioners
Discord with 1000+ members attending the conference.
Learn more about LLMs
Topics such as RAG, Evals, Inference, Fine-Tuning, are covered.
Learn about the best tools
We have curated the tools that we like the most. Credits for many of these tools are provided.
Learn about fine-tuning in-depth
This conference used to be a fine-tuning LLMs course. That course is still here, and takes place over the course of 4 workshops.
What’s included
Live sessions
Learn directly from Dan Becker & Hamel Husain in a real-time, interactive format.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
Maven Guarantee
This course is backed by the Maven Guarantee. Students are eligible for a full refund up until the halfway point of the course.
Course syllabus
34 live sessions • 13 lessons
Week 1
May
14
Fine-Tuning Workshop 1: When and Why to Fine-Tune an LLM
When and Why to Fine-Tune an LLM
Week 2
May
21
Fine-Tuning Workshop 2: Fine-Tuning with Axolotl (guest speakers Wing Lian, Zach Mueller)
May
23
Conference Talk: From prompt to model: fine tuning when you've already deployed LLMs in prod (with Kyle Corbitt)
May
24
Office Hours: Axolotl w/Wing Lian
May
24
Office Hours: FSDP, DeepSpeed and Accelerate w/Zach Mueller
Fine-Tuning with Axolotl
Week 3
May
27
Office Hours: Gradio w/ Freddy Boulton
May
28
Fine-Tuning Workshop 3: Instrumenting & Evaluating LLMs (guest speakers Harrison Chase, Bryan Bischof, Shreya Shankar, Eugene Yan)
May
29
Conference Talk: LLM Eval For Text2SQL w/ Ankur Goyal
May
29
Conference Talk: Prompt Engineering Workshop w/John Berryman
May
29
Conference Talk: Inspect, An OSS framework for LLM evals w/ JJ Allaire
May
30
Office Hours: Modal w/ Charles Frye
May
30
Office Hours: LangChain/LangSmith
May
31
Conference Talk: Napkin Math For Fine Tuning w/Johno Whitaker
May
31
Conference Talk: Train (almost) any llm model using 🤗 autotrain
May
31
Optional: Johno Whitaker round 2
Instrumenting and Evaluating LLM's for Incremental Improvement
Week 4
Jun
4
Fine-Tuning Workshop 4: Deploying Fine-Tuned Models (Guest speakers Travis Addair, Charles Frye, Joe Hoover)
Jun
5
Conference Talk: Best Practices For Fine Tuning Mistral w/ Sophia Yang
Jun
5
Conference Talk: Creating, curating, and cleaning data for LLMs w/Daniel van Strien
Jun
5
Conference Talk: Why Fine-Tuning is Dead w/ Emmanuel Ameisen
Jun
6
Conference Talk: Systematically improving RAG applications w/Jason Liu
Jun
6
Conference Talk: Build Applications For LLMs in Python, with Jeremy Howard & Johno Whitaker
Jun
7
Optional: Getting the most out of your LLM experiments w/ Thomas Capelle
Deploying Your Fine-Tuned Model
Week 5
Jun
10
Conference Talk: Slaying OOMs with PyTorch FSDP and torchao (with Mark Saroufim and Jane Xu)
Jun
10
Conference Talk: When to Fine-Tune? (with Paige Bailey)
Jun
11
Conference Talk: Beyond the basics of Retrieval for Augmenting Generation (w/ Ben Clavié)
Jun
11
Conference Talk: Modal: Simple Scalable Serverless Services With Charles Frye
Jun
11
Optional: Replicate Office Hours
Jun
11
Conference Talk: A Deep Dive on LLM Evaluation (w/ Hailey Schoelkepf)
Jun
12
Conference Talk: Language models on the command-line w/ Simon Willison
Jun
12
Office Hours: Predibase w/ Travis Addair
Jun
12
Conference Talk: Fine-Tuning OpenAI Models - Best Practices w/Steven Heidel
Jun
12
Optional: Fine Tuning LLMs for Function Calling
Week 6
Jun
18
Back to Basics for RAG w/Jo Bergum
Jun
20
Optional: LiveStream - Lessons From A Year of Building w/LLMs
What students are saying
Meet your instructors / conference organizers
Dan Becker
Dan Becker
Chief Generative AI Architect @ Straive
Dan has worked in AI since 2011, when he finished 2nd (out of 1350+ teams) in a Kaggle competition with a $500k prize. He contributed code to TensorFlow as a data scientist at Google and he has taught online deep learning courses to over 250k people. Dan has advised AI projects for 6 companies in the Fortune 100.
Hamel Husain
Hamel Husain
Founder @ Parlance Labs
Hamel is an ML engineer who loves building machine learning infrastructure and tools 👷🏼♂️. He leads or contribute to many popular open-source machine learning projects. His extensive experience (20+ years) as a machine learning engineer spans various industries, including large tech companies like Airbnb and GitHub.
Hamel is an independent consultant helping companies operationalize LLMs. At GitHub, Hamel lead CodeSearchNet, a large language model for semantic search that was a precursor to CoPilot, a large language model used by millions of developers.
Course schedule
4-6 hours per week
Tuesdays
1:00pm - 3:00pm EST
Interactive weekly workshops where you will learn the tools you will apply in your course project.
Weekly projects
2 hours per week
You will build and deploy an LLM as part of the course project. The course project is divided into four weekly project.
By the end, you will not only know about fine-tuning, but you will have hands-on experience doing it.