Tom

I have the same question like u. I am also wondering how does "gen" works. - If each time guidance use "gen" , and it calls LLM and put all...

> > > What you're talking about is training/finetuning which is theoretically possible on CPU but practically impossible/non-feasible on CPU only because you'll be training for literal months instead of...

> @Tom-0727 please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information. > > ``` > @microsoft-github-policy-service agree [company="{your company}"] >...

> Thanks! This looks like a great performance comparison to flush out where we need to speed things up. Will dig into it soon. I guess the reason might be...

> Just a followup note here. I am going to try and make this work, but it will require a revamp of how the template prefix / variables are stored...

> That is with the new version of Guidance. It is now 3x faster than langchain for this scenario (using text-davinci-003 for this test I got 47 seconds with langchain)....