Fine-tuning Large Language Models
This course is an interactive deep dive into the art of fine-tuning Large Language Models (LLMs). Week 1 covers a robust framework for the lifecycle of LLM projects, from research to deployment. In Week 2, we'll master the nuances of refining encoder models, emphasizing text comprehension tasks and Hugging Face deployment. Our final week will be a deep dive into optimizing decoders for text generation, exploring cutting-edge techniques like LoRA and QLoRA.
Course taught by expert instructors
Santi Adavani
Head of Product at PostgresML
Dr. Santi Adavani is an accomplished technology leader with a demonstrated history of driving innovation and delivering impactful software products. He currently serves as the Founding Member and Head of AI at PostgresML, where he leads the development of the company's cloud-based AI Database as a Service platform. Prior to this role, Dr. Adavani was the Founder and CTO of RocketML, where he was instrumental in driving the company's success. He spearheaded the development of high-performance computing (HPC) MLOps products and services that specialized in solving data science problems in a variety of industries, including energy, precision medicine, financial services, and healthcare.
The course
Learn and apply skills with real-world projects.
Software Engineers looking to learn more or work in machine learning fields
Data science and machine learning practitioners looking for practical learning in NLP to support their current work, including those completely new to NLP
Writing Python and an ability to find and read documentation of different libraries
Basic knowledge of machine learning
Try these prep courses first
- Learn
- What is Fine-tuning?
- Benefits of Fine-tuning
- A Fine-tuning framework - research, development, and production
Project- Evaluation module for both encoder and decoder models (including OpenAI GPT-3.5) for financial text classification problem.
- Learn
- What are Encoder models?
- Pre-training encoder models
- Fine-tuning Encoder models for specific tasks
- Factors affecting GPU utilization
- Data preparation, Tokenization, Data collation, Evaluation, Training and Deployment
Project- Fine-tune a BERT base encoder model on financial transaction data that outperform a 100B+ general purpose model
- Learn
- What are decoder models?
- Pre-training Decoder models
- Building blocks behind AI assistants like ChatGPT
- PEFT techniques - Low Rank Approximation (LoRA) and Quantized LoRA
- Data preparation, Tokenization, Data collation, Evaluation, Training and Deployment
Project- Fine-tune a GPT base decoder model on Alpaca instruction dataset to build a personal assistant
A course you'll actually complete. AI-powered learning that drives results.
AI-powered learning
Transform your learning programs with personalized learning. Real-time feedback, hints at just the right moment, and the support for learners when they need it, driving 15x engagement.
Live courses by leading experts
Our instructors are renowned experts in AI, data, engineering, product, and business. Deep dive through always-current live sessions and round-the-clock support.
Practice on the cutting edge
Accelerate your learning with projects that mirror the work done at industry-leading tech companies. Put your skills to the test and start applying them today.
Flexible schedule for busy professionals
We know you’re busy, so we made it flexible. Attend live events or review the materials at your own pace. Our course team and global community will support you every step of the way.
Completion certificates
Each course comes with a certificate for learners to add to their resume.
Best-in-class outcomes
15-20x engagement compared to async courses
Support & accountability
You are never alone, we provide support throughout the course.
Get reimbursed by your company
More than half of learners get their Courses and Memberships reimbursed by their company.
Hundreds of companies have dedicated L&D and education budgets that have covered the costs.
