Talk to us

Building & Fine-tuning LLM

3

Days

Online Live

Delivery Method

Specialty

Skill Level

$1,800 USD

Fee

Overview

This course offers a comprehensive understanding of key Large Language Models (LLMs) concepts, techniques, and fine-tuning strategies for LLMs. It’s designed for both ML beginners and professionals to advance their skills in the field of LLM. Participants will gain hands-on experience in working with LLM models, evaluating their performance, preparing data for fine-tuning, and applying advanced fine-tuning methods.

Completing this course will help you:

  • Understand the full LLM lifecycle.
  • Know the best strategies to use for a given NLP task.
  • Evaluate and optimize LLMs for performance, efficiency, and task-specific outcomes.
  • Apply practical data preparation techniques to optimize LLM fine-tuning workflows.
  • Customize LLMs using advanced fine-tuning techniques to meet different industry use cases.

Curriculum

  • Module 1 - Introduction to LLM & Lifecycle
    • Understand Transformers and different types of LLM architectures.
    • Explore the lifecycle of LLMs, from pre-training to instruction tuning, alignment, fine-tuning and distillation.
    • Understand how LLMs can be customized for domain-specific tasks.
  • Module 2 - Working with LLM
    • Learn how to work with LLMs such as GPT-4, Llama-3, Mistral, and Falcon.
    • Learn how to use encoder and decoder models for downstream prediction tasks.
  • Module 3 - LLM Evaluation
    • Learn the importance of a good evaluation framework.
    • Apply various metrics to evaluate the performance of LLMs.
    • Best practices on choosing the best evaluation approach for your project.
  • Module 4 - Data Prep for Fine-tuning
    • Learn how to preprocess data for LLM training and fine-tuning.
    • Understand the impact of dataset quality on model performance.
    • Learn how to do data augmentation and generate synthetic data.
  • Module 5 - Fine-tuning Methods
    • Use SetFit for LLMs parameter-efficient.
    • Fine-tune pre-trained LLMs using parameter-efficient fine-tuning (LoRA, QLoRA).
    • Compare different fine-tuning methods such as prefix tuning, PEFT, and their impact on performance and efficiency.
  • Module 6 - LLM Fine-tuning Project
    • Apply practical data preprocessing and instruction Fine-tuning techniques.
    • Gain end-to-end fine-tuning LLM experience with Llama-3.

Schedule

Online

Jan 06 - 08, 2025

9:30am - 4:30pm EST

Online

Mar, 2025

9:30am - 4:30pm EST

Online

Jul, 2025

9:30am - 4:30pm EDT

Contact Us
WeCloudData

WeCloudData is the leading data science and AI academy. Our blended learning courses have helped thousands of learners and many enterprises make successful leaps in their data journeys.

Sign up for newsletter

"*" indicates required fields

This field is for validation purposes and should be left unchanged.
Programs
Corporate Services
Resources
Company
Let’s Connect!
Facebook-f Twitter Linkedin Instagram Meetup

Canada:

180 Bloor St W #1003

Toronto, ON, Canada M5S 2V6

US:

16192 Coastal Hwy

Lewes, DE 19958, USA

info@weclouddata.com

Corporate Training Inquiry
Please include the date and time that you are interested in. If you couldn't find a suitable schedule, please leave us a note. Our program manager will get in touch.
This site is registered on wpml.org as a development site. Switch to a production site key to remove this banner.