Update README.md

README.md

@@ -63,6 +63,29 @@ Your output should be in JSON FORMAT with the keys "REASONING" and "SCORE":
 
 The model will output the score as 'PASS' if the answer is faithful to the document or FAIL if the answer is not faithful to the document. 
 
+## Inference
+
+To run inference, you can use HF pipeline:
+
+```
+pipe = pipeline(
+          "text-generation",
+          model="PatronusAI/Llama-3-Patronus-Lynx-8B-Instruct",
+          max_new_tokens=600,
+          device="cuda",
+          return_full_text=False
+        )
+
+messages = [
+    {"role": "user", "content": prompt},
+]
+
+result = pipe(messages)
+print(result[0]['generated_text'])
+
+```
+
+Since the model is trained in chat format, ensure that you pass the prompt as a user message.
 
 ## Training Details