Upload README.md with huggingface_hub

README.md

@@ -1,6 +1,5 @@
 ---
 inference: false
-pipeline_tag: visual-question-answering
 ---
 
 <br>
@@ -54,7 +53,20 @@ predictor = huggingface_model.deploy(
     instance_type="ml.g5.xlarge",
 )
 ```
+## Inference on SageMaker
 
+```python
+data = {
+    "image" : 'https://raw.githubusercontent.com/haotian-liu/LLaVA/main/images/llava_logo.png', 
+    "question" : "Describe the image and color details.",
+    # "max_new_tokens" : 1024,
+    # "temperature" : 0.2,
+    # "conv_mode" : "llava_v1"
+}
+output = predictor.predict(data)
+print(output)
+```
+Or use [SageMakerRuntime](https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/sagemaker-runtime/client/invoke_endpoint.html#invoke-endpoint) to setup endpoint invoking client.
 
 ## License
 Llama 2 is licensed under the LLAMA 2 Community License,