Updated readme file

README.md

@@ -10,6 +10,25 @@ pipeline_tag: image-to-text
 duplicated_from: Salesforce/blip2-opt-2.7b
 ---
 
+# Update to existing Salesforce model card:
+
+**Added handler to run mode on hugging face inference pipeline.**
+
+Input:
+```
+  {
+      "inputs": "<Base64 Image>",
+      "prompts": "<Prompt Text here>"
+  }
+```
+Output:
+```
+  {
+      "captions":"<Generated Image caption>"
+  }
+```
+
+
 # BLIP-2, OPT-2.7b, pre-trained only
 
 BLIP-2 model, leveraging [OPT-2.7b](https://huggingface.co/facebook/opt-2.7b) (a large language model with 2.7 billion parameters).