Update README.md

README.md

@@ -11,10 +11,18 @@ Multimodal model at the input and output.
 
 The SAPI-0 is a 15-billion-parameter multimodal model operating with only 0.5 billion active parameters, which accepts inputs of text, document, image, audio, and video, and can also generate outputs of text, document, image, audio, and video. Your context window is infinite and the model's reasoning is enabled through configuration.
 
+## Download
+
 ```bash
 sapilm --get schatmodels/s0
 ```
 
+## Inference
+
+```bash
+sapilm --load sapi-0
+```
+
 ## Contributing
 
 We do not accept contributions that may result in changing the original code.