Update README.md

README.md

@@ -17,7 +17,8 @@ base_model:
 
 # SmolVLM2-500M-Video
 
-SmolVLM2-500M-Video is a tiny video model, member of the SmolVLM family. It accepts video, arbitrary sequences of image and text inputs to produce text outputs. It's designed for efficiency. SmolVLM2 is optimized for video but can answer questions about images, describe visual content, or transcribe text. Its lightweight architecture makes it suitable for on-device applications while maintaining strong performance on multimodal tasks. It can run inference on a video with 1.8GB of GPU RAM.
+SmolVLM2-500M-Video is a model optimized for video that accepts video, arbitrary sequences of image and text inputs to produce text outputs. It can answer questions about media files, compare images,  describe visual content, or transcribe text.
+Its lightweight architecture makes it suitable for on-device applications while maintaining strong performance on multimodal tasks. It can run inference on a video with 1.8GB of GPU RAM.
 
 ## Model Summary