Квизы: NLP, Transformers & LLMs

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.

Средний Квизов: 5 · вопросов: 50 около 34 минуты
0/5сдано Экзамен по разделу 20 вопросов вперемешку. За 80% - сертификат.
Теги:
1 Tokenization & Embeddings Средний Learn how text becomes tokens and tokens become vectors that capture meaning. #nlp#tokenization 10 вопр. · ~6 мин Не начат Начать
2 The Attention Mechanism Сложный Queries, keys, values, softmax and the sqrt(d) scaling at the heart of every transformer. #attention#transformers 10 вопр. · ~8 мин Не начат Начать
3 Transformer Architecture Сложный Encoders, decoders, positional encoding, causal masks and multi-head attention, interview style. #transformers#interview 10 вопр. · ~8 мин Не начат Начать
4 How LLMs Generate Text Средний Next-token prediction, logits, context windows and the difference between greedy decoding and sampling. #llm#text-generation 10 вопр. · ~6 мин Не начат Начать
5 Fine-Tuning & RAG Средний When to fine-tune, when to retrieve, and the details that make retrieval-augmented generation work. #llm#rag 10 вопр. · ~6 мин Не начат Начать