Update README.md

README.md

@@ -63,7 +63,33 @@ This model card corresponds to the fp8-quantized version of Salamandra-2b-instru
 The entire Salamandra family is released under a permissive [Apache 2.0 license]((https://www.apache.org/licenses/LICENSE-2.0)).
 
 
-## Additional information
+## How to Use
+
+The following example code works under ``Python 3.9.16``, ``vllm==0.6.3.post1``, ``torch==2.4.0`` and ``torchvision==0.19.0``, though it should run on
+any current version of the libraries. This example provides a chat interface for the model.
+
+```
+from vllm import LLM, SamplingParams
+
+model_name = "BSC-LT/salamandra-2b-instruct-fp8"
+llm = LLM(model=model_name)
+
+messages = []
+
+while True:
+    user_input = input("user >> ")
+    if user_input.lower() == "exit":
+        print("Chat ended.")
+        break
+
+    messages.append({'role': 'user', 'content': user_input})
+
+    outputs = llm.chat(messages, sampling_params=SamplingParams(temperature=0.5, stop_token_ids=[5], max_tokens=200))[0].outputs
+    model_output = outputs[0].text
+    print(f'assistant >> {model_output}')
+    messages.append({'role': 'assistant', 'content': model_output})
+```
+
 
 ### Author
 International Business Machines (IBM).