- GenAI
- ComputerVision
- LLM
- Transformers
- YOLO
- NLP
- external-services
•
•
•
•
•
•
-
Retrieval-Augmented Generation (RAG): Building Knowledge-Aware LLM Systems
An advanced deep dive into Retrieval-Augmented Generation (RAG), covering architecture, embeddings, vector databases, and real-world trade-offs.
-
Fine-Tuning Large Language Models: From Full Training to Parameter-Efficient Methods
An advanced deep dive into fine-tuning LLMs, covering full fine-tuning, PEFT methods like LoRA, and real-world trade-offs.
-
Encoder vs Decoder: Understanding BERT, GPT and Modern LLM Architectures
A deep dive into encoder-only, decoder-only, and encoder-decoder architectures, and how models like BERT, GPT, and BART differ.
-
A Deep Dive into Attention: Self-Attention, Multi-Head Attention and Positional Encoding
A comprehensive guide to attention mechanisms in Transformers, including intuition, QKV, self-attention, multi-head attention, and positional encoding.
-
Transformer Architecture Explained: Attention is All You Need
A deep dive into Transformer architecture, including encoder-decoder structure, attention mechanism, positional encoding, and multi-head attention.