updated readme

README.md

@@ -10,6 +10,35 @@ widget:
 # Model Card: CLIP
 
 Disclaimer: The model card is taken and modified from the official CLIP repository, it can be found [here](https://github.com/openai/CLIP/blob/main/model-card.md).
+I just added a custom handler which is required for multimodal models like this one. 
+Custom handler present for CLIP model patch32, but not for the CLIP large patch14. Source: https://huggingface.co/philschmid/clip-zero-shot-image-classification
+
+## Python code to run this after deploying it with HuggingFace's dedicated endpoint
+import json
+from typing import List
+import requests as r
+import base64
+
+ENDPOINT_URL = ""
+HF_TOKEN = ""
+
+
+def predict(path_to_image: str = None, candiates: List[str] = None):
+    with open(path_to_image, "rb") as i:
+        b64 = base64.b64encode(i.read())
+
+    payload = {"inputs": {"image": b64.decode("utf-8"), "candiates": candiates}}
+    response = r.post(
+        ENDPOINT_URL, headers={"Authorization": f"Bearer {HF_TOKEN}"}, json=payload
+    )
+    return response.json()
+
+
+prediction = predict(
+    path_to_image="/Users/user/Downloads/....", candiates=["Item1", "Item2"]
+)
+
+prediction
 
 ## Model Details