Practice Mode

Quiz Modules

AI concepts · answer, learn, repeat

Attention Mechanisms

Foundations & Architecture

Why attention replaced recurrence, scaled dot-product attention, Q/K/V, multi-head attention, self vs cross attention, causal masking, positional encoding, and the KV cache.

CoreFree
30 questions · ~23 minStart
Advanced400 bits
30 questions · ~23 minStart

Transformer Architecture

Foundations & Architecture

Self-attention, Q/K/V, multi-head attention, positional encoding, residuals, layer norm, the FFN, embeddings, and the encoder/decoder stacks.

CoreFree
50 questions · ~38 minStart
Advanced400 bits
50 questions · ~38 minStart

RAG Fundamentals

RAG

The retrieve-then-generate pipeline: loading, chunking, embedding, retrieval, reranking, grounded generation, evaluation, hybrid search, and RAG vs fine-tuning.

CoreFree
50 questions · ~38 minStart
Advanced400 bits
50 questions · ~38 minStart

Model Context Protocol

Agents & Autonomy

Host/client/server architecture, tools/resources/prompts primitives, transports, JSON-RPC protocol, capability discovery, security model, and SDK patterns.

CoreFree
50 questions · ~38 minStart
Advanced400 bits
50 questions · ~38 minStart

Tokenization

Foundations & Architecture

Granularity levels, subword tokenization, the tokenizer pipeline, BPE, byte-level BPE, WordPiece, Unigram, SentencePiece, special tokens, and token counting.

Core250 bits
30 questions · ~23 minStart
Advanced400 bits
30 questions · ~23 minStart

Embeddings

Foundations & Architecture

Dense vectors, word2vec/GloVe/fastText, static vs contextual, sentence embeddings and SBERT, bi- vs cross-encoders, similarity metrics, contrastive learning, and Matryoshka.

Core250 bits
50 questions · ~38 minStart
Advanced400 bits
50 questions · ~38 minStart

LLM Training Pipeline

Training & Adaptation

Pretraining objective, data curation, scaling laws, Chinchilla, AdamW, LR schedules, mixed precision, distributed training, SFT, RLHF, DPO, training evaluation.

Core250 bits
50 questions · ~38 minStart
Advanced400 bits
50 questions · ~38 minStart

Fine-tuning & PEFT

Training & Adaptation

Full fine-tuning vs parameter-efficient methods: LoRA, QLoRA, adapters, prefix/prompt/P-tuning, freezing, rank and alpha, adapter merging, and when to fine-tune.

Core250 bits
50 questions · ~38 minStart
Advanced400 bits
50 questions · ~38 minStart

Quantization & Compression

Efficiency & Serving

Numeric formats, scale and zero-point, PTQ vs QAT, weight vs activation quantization, LLM.int8/GPTQ/AWQ/NF4, distillation, and pruning.

Core250 bits
50 questions · ~38 minStart
Advanced400 bits
50 questions · ~38 minStart

Inference Optimization

Efficiency & Serving

Prefill vs decode, KV cache, MQA/GQA, continuous batching, PagedAttention/vLLM, FlashAttention, speculative decoding, and serving metrics.

Core250 bits
50 questions · ~38 minStart
Advanced400 bits
50 questions · ~38 minStart

Showing 110 of 22 topics · 44 modules