Valerio Mariani

https://open-csr.github.io//methods/

is this dead? not optimal to delete the old vector store object everytime a refresh is needed...

+1

hi I applied the suggested changes with and fixed some other issues here in https://github.com/camelot-dev/excalibur/pull/183 while a was at it, I dockerized the app so we can just ```docker compose...

hi another dockerized and fixed version here https://github.com/camelot-dev/excalibur/pull/183 it not perfect but at least can use the app

hello, since I don't own any NVIDIA GPUs and can only deploy on paid, hosted solutions, I'd need cpu support for local development in order not to pay for development...

> AFAIK you can merge the LoRA weights and unquantised base model (even if you fine-tuned in 4/8 bit) using `model.merge_and_unload()`. You can then quantise this model using AQW and...