Kostenlos · ohne Anmeldung · ohne Zeitlimit
Fertige Multiple-Choice-Übungsquizze, von Hand geprüft. Löse jedes Gratis-Quiz online — jede Antwort kommt mit Erklärung, und jede Quiz-Seite hat einen vollständigen Lösungsschlüssel zum Wiederholen.
IT
Test your knowledge of transformer architectures, PEFT techniques (LoRA), RLHF, vLLM, and production deployment strategies. Beantworte jede Frage und sieh sofort, ob du richtig liegst — jedes Mal mit Erklärung.
Ein kostenloser Multiple-Choice-Übungstest mit 16 Fragen zu IT. Jede Frage hat eine richtige Antwort und eine kurze Erklärung, und der vollständige Lösungsschlüssel unter dem Quiz dient zugleich als Lernzettel. Kein Konto, kein Zeitlimit — löse ihn so oft du willst.
Dies ist ein kostenloses Multiple-Choice-Quiz mit 16 Fragen. Nach jeder Antwort siehst du, ob sie richtig war — immer mit Erklärung. Keine Anmeldung, kein Zeitlimit: Mach es so oft du willst und nutze den Lösungsschlüssel oben zum Wiederholen, vorher oder nachher.
Richtige Antwort: 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.
Richtige Antwort: 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.
Richtige Antwort: 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.
Richtige Antwort: 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.
Richtige Antwort: 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.
Richtige Antwort: BNormalFloat 4 (NF4)
QLoRA introduced NormalFloat 4 (NF4), an information-theoretically optimal quantile quantization scheme designed specifically for normally distributed neural network weights.
Richtige Antwort: 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.
Richtige Antwort: 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).
Richtige Antwort: 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.
Richtige Antwort: 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.
Richtige Antwort: 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.
Richtige Antwort: 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.
Richtige Antwort: 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.
Richtige Antwort: 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.
Richtige Antwort: 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.
Richtige Antwort: 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.