vikhyatk

/

moondream2

like 689

Waiting on this pull request to get merged: https://github.com/ggerganov/llama.cpp/pull/6899

it works with llama.cpp :
/whatever/llama.cpp/llava-cli -m /whatever/models/moondream2/moondream2-text-model-f16.gguf --mmproj /whatever/models/moondream2/moondream2-mmproj-f16.gguf --image /whatever/picture.jpg -p "describe the image" --temp 0.1 -c 2048

Works also with LM_Studio, just create a directory moondream2 with the two gguf files in your local model directory, mine is /home/alioune/LMStudio/models/alioune/local/
Use alpaca preset, set temp to 0.1, upload a picture, prompt for "describe image" ... profit!

it works with llama.cpp :
/whatever/llama.cpp/llava-cli -m /whatever/models/moondream2/moondream2-text-model-f16.gguf --mmproj /whatever/models/moondream2/moondream2-mmproj-f16.gguf --image /whatever/picture.jpg -p "describe the image" --temp 0.1 -c 2048

Works also with LM_Studio, just create a directory moondream2 with the two gguf files in your local model directory, mine is /home/alioune/LMStudio/models/alioune/local/
Use alpaca preset, set temp to 0.1, upload a picture, prompt for "describe image" ... profit!

awesome! thanks!