scalar27

use existing llama.cpp install

7

I've been using llama.cpp for quite a while (M1 Mac). Is there a way I can get ai_voicetalk_local.py to point to that installation instead of reinstalling it here? Sorry, newbie...

Please make a version that uses llama.cpp's server

1

Please consider making a version that uses llama.cpp's server instead of ollama. This would give better flexibility in terms of trying new models and settings. Thanks.

use llama.cpp instead of ollama

2

What would be involved in getting some of these apps, e.g., chat with pdf, to work with llama.cpp instead of ollama? I'm a big fan of llama.cpp (on a Mac)....

issue with wifi off

9

Newbie here, I'm trying to use this cool repo: https://github.com/PkmX/orpheus-chat-webui that uses fastrtc. I'm on a Mac M1 Max. It works fine when I have a wifi connection but fails...

trying to run Chatterbox on a M1 Mac

2

I'm trying to run Chatterbox on an M1 Mac. I'm getting this error: gradio.exceptions.Error: "Error: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are...

vibevoice model download stuck?

2

Trying to generate using VibeVoice for the first time, the terminal shows: Loading processor & model from microsoft/VibeVoice-Large Fetching 10 files: 0%| | 0/10 [00:00