Read: Transformer Architecture — Complete Int…
Start with the chapter spine
Open practice dock
Drills and weak-topic replay
Study library
Search all imported chapters
Llms
Continue from the last thing you actually touched, instead of hunting through the registry again.
ContinueNo assignments matching your criteria.
Try a broader filter or jump back to the course hub to browse the full assignment set.
Transformer Architecture — Complete Introduction
Deep dive into patterns and axioms.
Self-Attention and QKV Computation
Deep dive into patterns and axioms.
Multi-Head Attention Deep Dive
Deep dive into patterns and axioms.
Positional Encoding — Sinusoidal and Learned Embeddings
Deep dive into patterns and axioms.
Decoder Layer, Cross-Attention, and Teacher Forcing
Deep dive into patterns and axioms.
Layer Normalization & Residual Connections in Transformers
Deep dive into patterns and axioms.
Pre-training Objectives: Causal LM, Masked LM, and Beyond
Deep dive into patterns and axioms.
GPT Architecture: Decoder-Only Transformer & Autoregressive Generation
Deep dive into patterns and axioms.
BERT Architecture: Encoder-Only & Bidirectional Context
Deep dive into patterns and axioms.
Tokenization: BPE, WordPiece, SentencePiece
Deep dive into patterns and axioms.
Fine-tuning Methods: LoRA, Adapters, and PEFT
Deep dive into patterns and axioms.
Prompt Engineering: In-Context Learning, Chain-of-Thought
Deep dive into patterns and axioms.
RLHF, Alignment, and Constitutional AI
Deep dive into patterns and axioms.
Quantization, Pruning, Distillation & Fast Attention
Deep dive into patterns and axioms.