PromptEngineer

Good point, currently it store add the embeddings into the DB folder, will add this.

Currently, it will support models in the HF format. Will add support for other models.

@olafgeibig I will update it and will check if it still works. Thanks for bringing this up.

In the current version, no, will be adding the support.

Thanks for sharing it, this looks great. I do plan to add GUI support to it.

Can you provide more details one what you mean by 4 elements?

Thanks @vai. @sinaxvo1 for target location, check out here: https://github.com/PromtEngineer/localGPT#:~:text=Pretrained%20models%20are,tranformers%20installation%20page. @sinaxvo1 if this works, please close the issue.

I will probably need to add smaller-size embeddings to use by default. What is your Hardware configuration?

The issue is related to the required RAM on the system. I was able to reproduce this. The current implementation uses ~40GB of memory. I have tested a few models...

Yes, that would be awesome. I think if we can implement it as an option list of all compatible models (just like Oobabooga text generation webtui) that would be great....