These GGUF quants were made from https://huggingface.co/fancyfeast/llama-joycaption-beta-one-hf-llava and designed for use in KoboldCpp 1.91 and above.
Contains 3 GGUF quants of Joycaption Beta One, as well as the associated mmproj file.
To use:
- Download the main model (Llama-Joycaption-Beta-One-Hf-Llava-Q4_K.gguf) and the mmproj (Llama-Joycaption-Beta-One-Hf-Llava-F16.gguf)
- Launch KoboldCpp and go to Loaded Files tab
- Select the main model as "Text Model" and the mmproj as "Vision mmproj"
