NLP, Transformers & LLMs-Quizze

How language models turn text into tokens and vectors, how attention and the transformer work, and how large language models generate text, get fine-tuned and use retrieval.

Fortgeschritten 5 Quizze · 50 Fragen etwa 34 Minuten
0/5bestanden Kategorieprüfung 20 gemischte Fragen. Mit 80% gibt es ein Zertifikat.
Tags:
1 Tokenization & Embeddings Mittel Learn how text becomes tokens and tokens become vectors that capture meaning. #nlp#tokenization 10 Fragen · ~6 Min. Nicht begonnen Starten
2 The Attention Mechanism Schwer Queries, keys, values, softmax and the sqrt(d) scaling at the heart of every transformer. #attention#transformers 10 Fragen · ~8 Min. Nicht begonnen Starten
3 Transformer Architecture Schwer Encoders, decoders, positional encoding, causal masks and multi-head attention, interview style. #transformers#interview 10 Fragen · ~8 Min. Nicht begonnen Starten
4 How LLMs Generate Text Mittel Next-token prediction, logits, context windows and the difference between greedy decoding and sampling. #llm#text-generation 10 Fragen · ~6 Min. Nicht begonnen Starten
5 Fine-Tuning & RAG Mittel When to fine-tune, when to retrieve, and the details that make retrieval-augmented generation work. #llm#rag 10 Fragen · ~6 Min. Nicht begonnen Starten