llama implementation

app.py

@@ -4,8 +4,8 @@ import os
 
 HF_API_KEY = os.getenv("HF_API_KEY")  # Retrieve API key from environment variable
 
-models = ["HuggingFaceH4/zephyr-7b-beta", "microsoft/Phi-4-mini-instruct"]
-client = InferenceClient(model=models[1], token=HF_API_KEY)  # Pass API key to client
+models = ["HuggingFaceH4/zephyr-7b-beta", "microsoft/Phi-4-mini-instruct", "meta-llama/Llama-3.2-3B-Instruct"]
+client = InferenceClient(model=models[2], token=HF_API_KEY)  # Pass API key to client
 
 
 def respond(