Saifeddine ALOUI
Saifeddine ALOUI
Ok. Add_personality script installs the personality but doesn't set it to be used. You have to change the configs/config_local.yaml file to the right personality category and name
Yes, but i need to use a gpu compatible backend. Backends are very easy to build. All you have to do is look at llamacpp backend example and create another...
Yes, they have a file that contains the loading of all that jucy stuff. But I don't want to copy their code. Someone can create a repo with the backend...
Now gpt-j backend is supported with a simplified mode (no word by word output)
Ok, I assigned it to you
Hi and thanks. I'll try to purge my cache and reinstall the bindings again. I have no time to do it right now but i'll look it up this evening....
I made it work using this: on windows: ```cmd set BUILD_CUDA_EXT=0 ``` then ```cmd pip install auto-gptq ``` But there is no Cuda :(
in lord of llms, I had to do this in my install script: ```python # Step 2: Install dependencies using pip from requirements.txt env = os.environ.copy() env["BUILD_CUDA_EXT"] = "0" requirements_file...
Thank you marella for this. And I didn't see your chatdocs tool before; That's cool :) I was adding a new personality that allows you to do exactly that. You...
Your Binding as taking a place on the first row in my app, unfortunately people have issue installing it:  By the way, if you have an official Logo, I...