Created using https://github.com/ggerganov/llama.cpp/pull/4172

Basic usage (llama.cpp):

llava-cli -m <ShareGPT4V.gguf path> --mmproj <mmproj-model-f16.gguf path> -p "Describe image (or other prompt)" --image <image path>

License is the same as LLama 2/ShareGPT4V (https://huggingface.co/Lin-Chen/ShareGPT4V-7B)

Downloads last month
37
GGUF
Model size
6.74B params
Architecture
llama

16-bit

Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Spaces using Galunid/ShareGPT4V-gguf 2