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

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:

Downloads last month: 134

GGUF

Model size

312M params

Architecture

clip

16-bit

Inference Providers NEW

This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model's library.