Hello, I am running MedAgents' code and find it slow to get one answer (One question takes about 2~3 minutes). So I wonder if there is any method to speed it up. And how do you evaluate your methods on those datasets? How much time did it take?
If you use ChatGPT API calling it will be much slower. However, we are using Azure and we set up 300K TPM tokens per minute for gpt-35-turbo. It would be 30-50s per example.
Hello, I am running MedAgents' code and find it slow to get one answer (One question takes about 2~3 minutes). So I wonder if there is any method to speed it up. And how do you evaluate your methods on those datasets? How much time did it take?