Completed
- Explanation of training process and loss functions
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Advanced Embedding Models and Techniques for Retrieval Augmented Generation (RAG)
Automatically move to the next video in the Classroom when playback concludes
- 1 - Introduction to advanced video on embedding models for RAG systems
- 2 - Introduction to ModernBERT and its improved performance
- 3 - Overview of contextual document embeddings
- 4 - Explanation of ModernBERT family improvements
- 5 - Discussion of ModernBERT's faster runtime and quality metrics
- 6 - Explanation of periodic attention layers in ModernBERT
- 7 - Discussion of unpacked sequence feeding method
- 8 - Introduction to Nomic's fine-tuned ModernBERT model
- 9 - Explanation of Matryoshka embeddings for storage optimization
- 10 - Discussion of quantization options for memory reduction
- 11 - Introduction to contextual document embeddings approach
- 12 - Explanation of BM25 and why it works well
- 13 - Detailed explanation of contextual document embeddings process
- 14 - Presentation of performance results across different models
- 15 - Demonstration of creating embeddings with ModernBERT
- 16 - Demonstration of CDE model implementation
- 17 - Guide to fine-tuning embedding models
- 18 - Walkthrough of fine-tuning notebook setup
- 19 - Explanation of training process and loss functions
- 20 - Summary of tips for implementing embedding models
