Step1: Run "pip3 install transformers==4.6.1"
step2: RUN "pip3 install torch==1.9.0"
Step3: RUN "python3 download_HF_Question_Generation_summarization.py"
Step4: docker build -t summarization . Step5: docker run -p 80:80 --gpus all summarization
If you want to run the API indefinitely, use console applications like "Screen" GPU used: g4dn.xlarge AMI: Deep Learning Base AMI (Ubuntu 18.04) Version 42.0