Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B
Example usage with llama.cpp:
llama-cli \
-hf LiquidAI/LFM2.5-VL-3B-GGUF \
--temp 0.1 \
--min-p 0.15 \
--repeat-penalty 1.05
Then you can type /image <IMAGE PATH> to add an image to the chat, then ask What is in the image? or any other question about the image.
Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B
Example usage with llama.cpp:
llama-cli \
-hf LiquidAI/LFM2.5-VL-3B-GGUF \
--temp 0.1 \
--min-p 0.15 \
--repeat-penalty 1.05
Then you can type /image <IMAGE PATH> to add an image to the chat, then ask What is in the image? or any other question about the image.