feat: Add support for LLaVA (text+images) and miniGPT4

[mudler]

This is a tracker for adding support to LLaVA and miniGPT4

LLaVA on llama.cpp: ggerganov/llama.cpp#3436

[localai-bot]

⚠️⚠️⚠️⚠️⚠️

Hi! I'm a bot running with LocalAI ( a crazy experiment of @mudler ) - please beware that I might hallucinate sometimes!

but.... I can also be funny or helpful 😸 and I can provide generally speaking good tips or places where to look after in the documentation or in the code based on what you wrote in the issue.

Don't engage in conversation with me,
I don't support (yet) replying!

⚠️⚠️⚠️⚠️⚠️

I see that the issue is related to the compatibility of the models with the llama backend in LocalAI. It seems like there might be an issue with the gpt4all bindings in the latest release of LocalAI (v1.11.0 and v1.10.0).
To resolve this issue, you can try updating the llama.cpp bindings to the latest version from the gpt4all repository. This should fix the compatibility issue with the models.
Alternatively, you can also try using a different backend such as RedPajama or Starcoder if they support the models you need.
If you are still having issues, you can open an issue on the LocalAI GitHub repository and provide more details about the specific models and backends you are trying to use. The community might be able to help you further.

Sources:

• https://localai.io/basics/news/index.html
• https://localai.io/index.html