Branko Radovanović

See also #1779.

If I understand correctly it would be something like side-by-side Chatbot Arena (https://chat.lmsys.org/?arena). Trouble is, running two models simultaneously would probably require at least 32 Gb of RAM. It would...

> This is a very old CPU, which we do not support. GPT4All requires a processor that supports AVX instructions, which are only available in CPUs from 2016 and newer....

> It is, because loading a model is super slow. Imagine, you have 5 -10 conversations and you want to delete them all, which easily can happen, so you have...

Also, if I'm not mistaken, if one clones the model in Model/Character settings, so that it's effectively the same model, only with e.g. different temperature, it still gets treated as...

Looks like this is no longer the case in 2.6.2. Switching between chats is fast now, so models are clearly not loaded in the process. I believe this issue can...

> not really ... i had 12 chats and yes if you delete, it does not load the model ... but after 4 chats the whole programm stucks (froze) and...

When one changes the system prompt, one effectively changes the model settings. I think the best way of working (or experimenting) with multiple system prompts is to clone the model...

> Just an opinion, people will then ask to support [SOLAR](https://huggingface.co/TheBloke/SOLAR-10.7B-Instruct-v1.0-GGUF), then X then Y...etc. I think it's time to expend the architecture to support any future model which an...

> Also no success with TheBloke's GGUF versions so far. trying out different versions now. > > I just get a generic error message in the client. Can anyone tell...