Description
LLM Apps: Prototyping, Model Evaluation, and Improvements. This course teaches participants how to develop applications based on large language models from prototyping to performance evaluation and optimization. The course focuses on understanding the concepts of prototyping, evaluation, and benchmarking with the aim of unlocking the full potential of these models. Participants will learn the full development stages, from building and selecting models to fine-tuning, testing, and benchmarking using industry-standard tools. Topics include setting up a development environment with Python and VS Code, understanding the principles of AI and machine learning, and selecting the right model for various applications such as natural language processing and computer vision. It also covers using technologies such as retrieval and additive manufacturing to improve the accuracy of outputs, working with the Hugging Face platform, and optimizing models through hyperparameter tuning. The course includes advanced techniques such as cross-validation to prevent overfitting and benchmarking models against standards such as GLUE and CIFAR-10. Participants will be introduced to confusion matrix analysis and metrics such as accuracy and F1 score to evaluate the performance of classification models, and will work with agent-based frameworks such as Autogen and Flowise AI. This course will provide the skills necessary to build efficient and powerful AI applications.
What you will learn
- Understanding technology and the landscape of LLM-based applications.
- Knowing when to use GEN AI (Generative Artificial Intelligence) and when to use Weak AI (Weak Artificial Intelligence).
- Installing and setting up the tools required to integrate artificial intelligence with standard applications (Standard APP).
- Learn the basics of artificial intelligence in the “Introduction to AI” module.
- An overview of machine learning types.
- Understanding the Data Lifecycle – How data evolves with your ML model.
- Introduction to the Foundation Model lifecycle.
- Fine tuning of models through data.
- Fine tuning of models via prompt.
- Fine tuning of models through hyperparameters.
- Using Huggingface models for work.
- Familiarity with agentic frameworks such as Autogen, Browser User, and Flowise AI.
- Understanding RAG and how to assess it.
- LLM assessment using the RAGAs standardization framework.
- Understanding the Confusion Matrix including accuracy, recall, and F1 score.
- Introduction to the GLUE standardization framework.
- Retrain and fine tune a computer vision model.
This course is suitable for people who:
- AI enthusiasts who are eager to get into LLM prototyping and evaluation.
- Developers looking to build and refine advanced AI models.
- Data scientists who want to reliably benchmark AI performance.
- Anyone interested in understanding AI model evaluation techniques.
- Every software engineer.
- Developers.
- Artificial intelligence engineers.
- Project managers.
- Product Owners.
- Artificial intelligence test engineers.
Course details
- Publisher: Udemy
- Lecturer: Dan Andrei Bucureanu
- Training level: Beginner to advanced
- Training duration: 5 hours and 53 minutes
- Number of lessons: 69
Course headings
LLM Apps: Prototyping Model Evaluation and Improvements Course Prerequisites
- Some AI Experience
- Experience with Prompting
- Some coding experience with Python
- Laptop able to run VS code and some python apps
- LLM Api key
- 7-8 hours and it will improve
Course images
Sample course video
Installation Guide
After Extract, view with your favorite player.
Subtitles: None
Quality: 720p
Download link
Downloadly
Rapidgator link
File(s) password: www.downloadly.ir
File size
3.1 GB
