Ettore Di Giacinto

> happens on my AIO image freshly updated from the latest tag @mudler Latest tag doesn't have the fix yet, only master images

I will try to test this locally soon - I was facing https://github.com/mudler/LocalAI/pull/3377 to start with that made unpractical to test this scenario, will report soon-ish.

> Any news on this? > I am facing the same issue with a M60 and Docker (latest cuda12). > Using different models or jumping from image generation to chat...

I guess that would work already with llama.cpp GGUF models if/when is getting supported in there ( see also https://github.com/ggerganov/llama.cpp/issues/9440 ). I'd change the focus of this one to be...

See also: https://github.com/ggerganov/llama.cpp/issues/9455

> BTW: "(Coming very soon) 11B and 90B Vision models > > 11B and 90B models support image reasoning use cases, such as document-level understanding including charts and graphs and...

> It seems they work independently on that [ollama/ollama#6963](https://github.com/ollama/ollama/pull/6963) that looks only golang-side of things to fit the images. The real backend changes seems to be in https://github.com/ollama/ollama/pull/6965

Thanks for raising this up, confirmed and patch release is on its way already :+1:

this should be fixed in 2.24.1

> IMO, we should not do this. Not handling PRIVATE keys in web its nice and we cnanot be held responsible for losing them. > Nothing forbids to run the...