FiditeNemini/Llama-3.1-Unhinged-Vision-8B-GGUF

Meta Llama 3.1 8B Model Combination

This is an ablated Meta Llama 3.1 8B model, combined with a mmprojector model designed for Llama 3.0, converted to GGUF.

The base Llama 3.1 appears to have been trained on multimodal content, and with the new 128K context, seems to have the necessary context to be able to talk about at least two separate images in a chat without confusing the two.