Edit model card

INOFFICIAL for testing only.

Update llama.cpp to b2737 and later and run:

./llava-cli -m ggml-model-Q8_0.gguf --mmproj moondream2-mmproj-f16.gguf --image llamas.png --temp 0.1 -e -p "\n\nQuestion: Describe this image.\n\nAnswer:"  -ngl 25
Downloads last month
1,197
GGUF
Model size
1.42B params
Architecture
phi2
+1
Unable to determine this model's library. Check the docs .

Quantized from