NVIDIA · NCA-GENL
The measurement thread
How you'd know the model is wrong. Opens in M01 building a crude 20-item eval set, re-runs that same instrument through RAG, metrics, experimentation and fine-tuning, and closes in M12 when production monitoring uses it to catch drift — the build's validator becomes the decay detector.
T1 · 95 lessons across 12 modules
- M0101-01Next-token prediction: what a language model is trained to do
- M0101-02LLM parameters: what they are and where knowledge is stored
- M0101-03Tensor shapes in transformers: batch, sequence, and hidden size
- M0101-04Vectors, dot products, and cosine similarity
- M0101-05Loss functions and cross-entropy explained
- M0101-06Gradient descent and backpropagation
- M0101-07Train, validation, and test splits
- M0101-08How to build an evaluation set for an LLM project
- M0202-01Why text must be converted to numbers
- M0202-02Tokens, vocabulary, and subword tokenization
- M0202-03Counting tokens: why tokens are not words
- M0202-04BPE vs WordPiece vs SentencePiece: which model uses which
- M0202-05Stemming vs lemmatization, and stop-word removal
- M0202-06Bag-of-words, TF-IDF, and n-grams
- M0303-01What text embeddings are: learned dense vectors
- M0303-02Token embeddings vs sentence and document embeddings
- M0303-03How to choose an embedding model
- M0303-04How to test retrieval quality by hand
- M0303-05Vector arithmetic and word analogies (word2vec)
- M0505-01Zero-shot vs few-shot prompting and in-context learning
- M0505-02How to structure a prompt: instruction, context, and format
- M0505-03Chain-of-thought prompting: when it helps and when it misleads
- M0505-04Prompt templates, versioning, and testing
- M0505-05Getting structured JSON output from an LLM
- M0505-06Prompt, RAG, or fine-tune? A first decision rule
- M0606-01Document parsing for RAG: PDFs, tables, and silent failures
- M0606-02Chunking strategies for RAG: fixed, recursive, and semantic
- M0606-03Metadata in RAG: what to embed versus what to return
- M0606-04Deduplication and corpus cleaning for RAG
- M0707-01Sparse retrieval and BM25 keyword search
- M0707-02Dense retrieval with embeddings
- M0707-03Limits of embedding search: negation, recency, and authority
- M0707-04Vector databases and ANN indexes (HNSW, IVF)
- M0707-05Access control and permissions in RAG retrieval
- M0707-06Hybrid search: combining keyword and vector retrieval
- M0707-07Reranking with a cross-encoder
- M0707-08Assembling context: chunk order and the lost-in-the-middle problem
- M0707-09The complete RAG pipeline, stage by stage
- M0707-10Debugging RAG: retrieval failure versus generation failure
- M0707-11Grounding, citations, and letting a model say I don't know
- M0707-12When RAG is the wrong tool
- M0808-01How to curate a dataset for an LLM task
- M0808-02Data quality problems: label noise, leakage, imbalance, and drift
- M0808-03Exploratory data analysis (EDA) on a text corpus
- M0808-04Choosing the right chart: histogram, box plot, scatter, bar, heatmap, line
- M0808-05NVIDIA RAPIDS: cuDF, cuML, and cuGraph for GPU data science
- M0909-01Scaling an evaluation set to a hundred items
- M0909-02Perplexity: what it measures and what it misses
- M0909-03Human evaluation: rubrics and inter-annotator agreement
- M0909-04BERTScore and embedding-based evaluation metrics
- M0909-05How to choose an evaluation metric: loss functions, R², precision vs recall
- M0909-06BLEU vs ROUGE vs exact match: which metric for which task
- M0909-07RAG evaluation metrics: faithfulness, relevance, and context recall
- M0909-08Cross-validation: k-fold, stratified, and when not to use it
- M0909-09Sample size and statistical significance in LLM evaluation
- M0909-10LLM-as-a-judge: how it works and where it fails
- M0909-11Reproducibility: why temperature 0 is not deterministic
- M0909-12Why LLMs hallucinate, and the types of hallucination
- M0909-13Error analysis: turning failures into a fix list
- M1010-01Public benchmarks (GLUE, MMLU) and data contamination
- M1010-02Zero-shot and few-shot capability testing
- M1010-03A/B testing an LLM feature in production
- M1010-04Regression testing an LLM system in CI/CD
- M1111-01Pretraining vs continued pretraining vs instruction tuning
- M1111-02Supervised fine-tuning (SFT): what it can and cannot change
- M1111-03Catastrophic forgetting when fine-tuning
- M1111-04GPU memory requirements for training an LLM
- M1111-05LoRA and parameter-efficient fine-tuning (PEFT)
- M1111-06RLHF: reinforcement learning from human feedback explained
- M1111-07Reward models, reward hacking, and preference data
- M1111-08Prompt vs RAG vs fine-tuning: the full decision rule
- M1111-09Choosing a model adaptation strategy under real constraints
- M1212-01Numeric precision: FP32, TF32, FP16, BF16, and INT8
- M1212-02Quantization: PTQ vs QAT and recovering accuracy
- M1212-03Reading loss curves to diagnose a training run
- M1212-04Distributed training: data parallelism, AllReduce, and NCCL
- M1212-05The KV cache and why LLM generation is memory-bound
- M1212-06Batching for inference: static, dynamic, and continuous
- M1212-07PagedAttention and vLLM: virtual memory for the KV cache
- M1212-08ONNX, TensorRT, and TensorRT-LLM: compiling a model for inference
- M1212-09LLM cost per million tokens, per request, and per month
- M1212-10Latency and throughput: TTFT, tokens per second, and p95
- M1212-11Multi-turn chat history and query rewriting
- M1212-12Keeping a vector index fresh: re-embedding and migration
- M1212-13Deploying with NVIDIA Triton Inference Server and NIM
- M1212-14Monitoring an LLM in production and detecting drift
- M1313-01NVIDIA's four pillars of trustworthy AI and how to implement each
- M1313-02NVIDIA NeMo Guardrails and content moderation for LLM applications
- M1313-03Prompt injection and indirect injection through RAG
- M1313-04Bias in AI: sources, measurement, and mitigation
- M1313-05Data privacy, consent, and why model weights cannot forget
- M1313-06Transparency, explainability, and model cards for LLM systems
- M1313-07AI energy use, carbon, and efficient inference
- M1313-08A trustworthy AI checklist for your own LLM service
- M1313-09How to read an AI research paper and track new LLM trends
Part of the throughlines running across the NCA-GENL prep course.