Skip to main content
. 2024 Oct 3;26:e60601. doi: 10.2196/60601

Table 7.

Estimated inference time and computational resources required for the generative tasks in Ascle.

Tasks Estimated inference time Computational resource
Question Answering
  • LLaMA2-13b: <60 s/itema

  • GPT4: <15 s/item

  • LLaMA2-13b: 4 * NVIDIA A100 GPU

  • GPT4: OpenAI APIb

Text Summarization <2 s/item 1 * NVIDIA V100 GPU
Text Simplification <2 s/item 1 * NVIDIA V100 GPU
Machine translation <2 s/item 1 * NVIDIA V100 GPU

as/item: seconds per item.

bAPI: application programming interface.