Za darmo · bez rejestracji · bez limitu czasu
Gotowe quizy z pytaniami zamkniętymi, sprawdzone ręcznie. Rozwiąż dowolny darmowy quiz online — każda odpowiedź ma wyjaśnienie, a każdy quiz pełny klucz odpowiedzi do powtórki.
Wczytywanie quizów
Za darmo · bez rejestracji · bez limitu czasu
Gotowe quizy z pytaniami zamkniętymi, sprawdzone ręcznie. Rozwiąż dowolny darmowy quiz online — każda odpowiedź ma wyjaśnienie, a każdy quiz pełny klucz odpowiedzi do powtórki.
IT
Test your knowledge of transformer architectures, PEFT techniques (LoRA), RLHF, vLLM, and production deployment strategies. Odpowiadaj na pytania i od razu sprawdzaj, czy to dobra odpowiedź — zawsze z wyjaśnieniem.
Darmowy test próbny z 16 pytaniami zamkniętymi z kategorii IT. Każde pytanie ma jedną poprawną odpowiedź i krótkie wyjaśnienie, a pełny klucz odpowiedzi pod quizem służy jako ściąga do nauki. Bez konta, bez limitu czasu — rozwiązuj, ile chcesz.
To darmowy quiz z 16 pytaniami zamkniętymi. Po każdej odpowiedzi zobaczysz, czy była poprawna, razem z wyjaśnieniem. Bez rejestracji i bez limitu czasu — rozwiązuj go, ile razy chcesz, a klucz odpowiedzi powyżej wykorzystaj do powtórki przed quizem albo po nim.
Poprawna odpowiedź: AIt freezes the base model weights and injects trainable low-rank rank decomposition matrices into attention layers
LoRA freezes the original pre-trained weights and adds pairs of low-rank matrices to attention projections, drastically reducing the number of trainable parameters and optimizer state memory.
Poprawna odpowiedź: BDPO directly optimizes the policy network using preference data without training a separate reward model
DPO mathematically reformulates the RL objective, directly updating the policy network from preferred/rejected human pairs without training a separate reward model or using complex PPO reinforcement learning.
Poprawna odpowiedź: AFragmentation and overallocation of the Key-Value (KV) cache in GPU VRAM
PagedAttention treats the dynamically growing KV cache like virtual memory pages in an operating system, eliminating memory fragmentation and enabling efficient KV cache sharing across requests.
Poprawna odpowiedź: BA small, fast draft model generates candidate tokens verified in parallel by the target model in a single forward pass
Speculative decoding uses a lightweight draft model to propose multiple tokens quickly; the larger, expensive model verifies or rejects them in parallel in one forward pass, boosting throughput.
Poprawna odpowiedź: AMemory reads and writes between fast GPU SRAM and high-bandwidth memory (HBM)
FlashAttention tiles the computation of softmax and attention matrices, reducing quadratic memory traffic between slow HBM and fast on-chip SRAM to make attention I/O-aware.
Poprawna odpowiedź: BNormalFloat 4 (NF4)
QLoRA introduced NormalFloat 4 (NF4), an information-theoretically optimal quantile quantization scheme designed specifically for normally distributed neural network weights.
Poprawna odpowiedź: BThe sharpness of the probability distribution over the vocabulary prior to sampling
Dividing logits by temperature scales the distribution: lower temperatures (<1.0) peak the distribution around high-probability tokens, while higher temperatures flatten it, increasing diversity.
Poprawna odpowiedź: BPositions outside the trained frequency domain cause severe perplexity degradation unless position interpolation or scaling is applied
RoPE encodes position via complex rotation angles; exceeding trained token lengths causes out-of-distribution rotation frequencies, degrading output quality unless scaled (e.g., via NTK-aware scaling).
Poprawna odpowiedź: BScheduling and evicting individual requests at each token iteration rather than at the full sequence level
Continuous batching inserts new requests and completes finished sequences at every single token generation step, maximizing GPU compute utilization compared to static request batching.
Poprawna odpowiedź: BIt discounts the logits of tokens that have already been generated to discourage loops
Repetition penalty reduces the logit value of previously generated tokens, making the sampling algorithm significantly less likely to select them again.
Poprawna odpowiedź: APrefill processes the prompt tokens in parallel to generate the initial KV cache; decode generates one token at a time autoregressively
The prefill phase is compute-bound, ingesting the full prompt concurrently to populate the KV cache; the subsequent decode phase is memory-bandwidth-bound, emitting one token per step.
Poprawna odpowiedź: BTo establish high-priority behavioral constraints, persona, and guidelines that persist throughout the interaction
System prompts provide foundational framing, safety boundaries, role-playing personas, and instructions that anchor model behavior throughout downstream conversation turns.
Poprawna odpowiedź: BThe loss of previously acquired general capabilities when a model is heavily trained on a narrow domain dataset
Catastrophic forgetting occurs when gradient updates on a specialized task overwrite the general linguistic and reasoning representations learned during large-scale pre-training.
Poprawna odpowiedź: ATime to First Token (TTFT)
Time to First Token (TTFT) measures the latency between dispatching a prompt and receiving the very first streamed token, defining perceived interactive responsiveness.
Poprawna odpowiedź: AA high-performance file format designed for rapid loading and execution on CPUs and GPUs via llama.cpp
GGUF is a extensible binary format created by the llama.cpp project that encapsulates model metadata, tensor data, and quantized weights for cross-platform local execution.
Poprawna odpowiedź: BTo prevent the policy model from drifting too far from the original reference model's generation distribution
A Kullback-Leibler (KL) divergence penalty ensures that the policy being updated with RL does not deviate drastically from the unaligned base model, preventing reward hacking and gibberish outputs.