Andriy Mulyar

Given how sensitive each model is to prompt templates, linking the backend together with per model prompt templates is likely something we want in the backend bindings. That being said,...

Yes, let's get C# bindings in! PR them to a subdirectory of the gpt4all-bindings directory!

Yeah please submit any of the models you like (huggingface checkpoints are on the Nomic HF account). Would be cool to see some numbers. I personally do not believe their...

Ah yes they compute ELO on human rankings. I was referring to the vicuna eval here https://lmsys.org/blog/2023-03-30-vicuna/ Like I said, would be happy if someone submitted snoozy into it! On...

See docs.gpt4all.io for details about why local LLMs may be slow on your computer. GPU support is in development and many issues have been raised about it. Closing.

Thanks for the report, we are aware and fixing all bindings currently!

What is the current prompt and input being used to produce short summary for the conversation name @cebtenzzre ?

📉

[Fuyu 8b](https://www.adept.ai/blog/fuyu-8b) is interesting because its decoder only. I think LLaVA style is a fine choice though for an initial multimodal implementation

Taking a look @Icemaster-Eric . I'm really excited about supporting plugin calling against open ai's plugin sepc but need to think about edge cases 1. prompt templates differ by model...