Quiz Part II
Short-Answer Questions
11. Briefly explain the difference between ROUGE and BERTScore.
12. Provide a use case where deploying a transformer model on edge devices (e.g., using TensorFlow Lite) would be beneficial.
13. What does the attention_mask input represent in transformer models, and why is it important during inference?
14. When deploying an NLP model with FastAPI, why might you choose to use a GPU for the server?
15. Describe the role of Gradio in deploying models on Hugging Face Spaces.
Short-Answer Questions
11. Briefly explain the difference between ROUGE and BERTScore.
12. Provide a use case where deploying a transformer model on edge devices (e.g., using TensorFlow Lite) would be beneficial.
13. What does the attention_mask input represent in transformer models, and why is it important during inference?
14. When deploying an NLP model with FastAPI, why might you choose to use a GPU for the server?
15. Describe the role of Gradio in deploying models on Hugging Face Spaces.
Short-Answer Questions
11. Briefly explain the difference between ROUGE and BERTScore.
12. Provide a use case where deploying a transformer model on edge devices (e.g., using TensorFlow Lite) would be beneficial.
13. What does the attention_mask input represent in transformer models, and why is it important during inference?
14. When deploying an NLP model with FastAPI, why might you choose to use a GPU for the server?
15. Describe the role of Gradio in deploying models on Hugging Face Spaces.
Short-Answer Questions
11. Briefly explain the difference between ROUGE and BERTScore.
12. Provide a use case where deploying a transformer model on edge devices (e.g., using TensorFlow Lite) would be beneficial.
13. What does the attention_mask input represent in transformer models, and why is it important during inference?
14. When deploying an NLP model with FastAPI, why might you choose to use a GPU for the server?
15. Describe the role of Gradio in deploying models on Hugging Face Spaces.