PromptEngineer

I tested it with device_type cpu and mps, have yet to try with cuda ________________________________ From: Austin ***@***.***> Sent: Monday, July 3, 2023 1:47:54 AM To: PromtEngineer/localGPT ***@***.***> Cc: PromptEngineer...

Yes, that didn't work. I was able to run an earlier commit. ________________________________ From: Austin ***@***.***> Sent: Monday, July 3, 2023 8:07:58 AM To: PromtEngineer/localGPT ***@***.***> Cc: PromptEngineer ***@***.***>; Mention...

That was the one before the restructuring of the dB into package. Will look it up when I have access to my laptop. ________________________________ From: Austin ***@***.***> Sent: Monday, July...

I will add flag for it.

@imjwang Yes, that would be great.

The option has been added.

@teleprint-me I agree with you, this could be a better solution. However, my thought process is if someone has a GPU on their system, then localGPT should use that by...

Makes sense and I like the approach. Can you please create a PR with updates to the Readme? Thanks

Yes, and thank you for your kind words.

Are you running it on a GPU?