Articles
6 articles across all categories
- Applications
Retrieval-Augmented Generation
Combining retrieval systems with generative models to produce accurate, grounded responses that go beyond the training data.
Read article → - Training
Fine-tuning LLMs
Adapting pre-trained LLMs to specific tasks: instruction tuning, RLHF, LoRA, and QLoRA.
Read article → - Architectures
Attention Mechanisms
A deep dive into attention mechanisms: scaled dot-product attention, cross-attention, and flash attention.
Read article → - Architectures
Transformer Architecture
The "Attention Is All You Need" paper revolutionized NLP. Understanding the encoder-decoder structure, multi-head attention, and positional encodings.
Read article → - Fundamentals
Backpropagation
The algorithm behind training neural networks — from computing gradients via the chain rule to updating weights with gradient descent.
Read article → - Fundamentals
Tokenization
How text is split into tokens for LLM input: BPE, WordPiece, SentencePiece, and the vocabulary trade-offs.
Read article →