i’m using the gpt-3.5-turbo model. I am using prompts in the model and the token count is increasing. The slowdown is increasing in direct proportion to the number of tokens. How can I deal with this, it’s too slow to be used.
i’m using the gpt-3.5-turbo model. I am using prompts in the model and the token count is increasing. The slowdown is increasing in direct proportion to the number of tokens. How can I deal with this, it’s too slow to be used.