Hello, First thanks a lot for this project, its great!
I was wondering if it is normal that hugchat responses take a lot of time? and what are the factors that can improve this issue?
If we take this query for example:
"Hello, Can you write a description of a recipe in English for chocolate cookies? include the following information separated by "!!": Ingredients, time, budget and method."
It takes more than 45 seconds to get the answer via hugchat api, but less than 8 seconds (to finish the whole answer) through hugging chat GUI. In both cases I used the model "microsoft/Phi-3-mini-4k-instruct"
Thank you !
Hello, First thanks a lot for this project, its great! I was wondering if it is normal that hugchat responses take a lot of time? and what are the factors that can improve this issue? If we take this query for example: "Hello, Can you write a description of a recipe in English for chocolate cookies? include the following information separated by "!!": Ingredients, time, budget and method." It takes more than 45 seconds to get the answer via hugchat api, but less than 8 seconds (to finish the whole answer) through hugging chat GUI. In both cases I used the model "microsoft/Phi-3-mini-4k-instruct" Thank you !