Most up-to date version of our Llama3-Llava (Based on Llava 1.5) series of mmproj files.

Projector Extracted from: (updated) https://huggingface.co/weizhiwang/LLaVA-Llama-3-8B Thank @weizhiwang for their work!

  • You must use the latest versions of Koboldcpp.

  • You can load the mmproj by using the corresponding section in the interface:

image/png

Downloads last month
170
GGUF
Model size
312M params
Architecture
clip
Hardware compatibility
Log In to view the estimation
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support