최신NVIDIA Generative AI LLMs - NCA-GENL무료샘플문제
문제1
In the context of language models, what does an autoregressive model predict?
In the context of language models, what does an autoregressive model predict?
정답: C
설명: (KoreaDumps 회원만 볼 수 있음)
문제2
Which principle of Trustworthy AI primarily concerns the ethical implications of AI's impact on society and includes considerations for both potential misuse and unintended consequences?
Which principle of Trustworthy AI primarily concerns the ethical implications of AI's impact on society and includes considerations for both potential misuse and unintended consequences?
정답: B
설명: (KoreaDumps 회원만 볼 수 있음)
문제3
Why is layer normalization important in transformer architectures?
Why is layer normalization important in transformer architectures?
정답: D
설명: (KoreaDumps 회원만 볼 수 있음)
문제4
In evaluating the transformer model for translation tasks, what is a common approach to assess its performance?
In evaluating the transformer model for translation tasks, what is a common approach to assess its performance?
정답: A
설명: (KoreaDumps 회원만 볼 수 있음)
문제5
What is the prompt "Translate English to French: cheese =>" an example of?
What is the prompt "Translate English to French: cheese =>" an example of?
정답: D
설명: (KoreaDumps 회원만 볼 수 있음)
문제6
In large-language models, what is the purpose of the attention mechanism?
In large-language models, what is the purpose of the attention mechanism?
정답: C
설명: (KoreaDumps 회원만 볼 수 있음)
문제7
In the context of transformer-based large language models, how does the use of layer normalization mitigate the challenges associated with training deep neural networks?
In the context of transformer-based large language models, how does the use of layer normalization mitigate the challenges associated with training deep neural networks?
정답: C
설명: (KoreaDumps 회원만 볼 수 있음)
문제8
Which of the following is a parameter-efficient fine-tuning approach that one can use to fine-tune LLMs in a memory-efficient fashion?
Which of the following is a parameter-efficient fine-tuning approach that one can use to fine-tune LLMs in a memory-efficient fashion?
정답: D
설명: (KoreaDumps 회원만 볼 수 있음)
문제9
Which of the following tasks is a primary application of XGBoost and cuML?
Which of the following tasks is a primary application of XGBoost and cuML?
정답: A
설명: (KoreaDumps 회원만 볼 수 있음)
문제10
When fine-tuning an LLM for a specific application, why is it essential to perform exploratory data analysis (EDA) on the new training dataset?
When fine-tuning an LLM for a specific application, why is it essential to perform exploratory data analysis (EDA) on the new training dataset?
정답: D
설명: (KoreaDumps 회원만 볼 수 있음)