Update app.py

app.py

@@ -4,14 +4,11 @@ from huggingface_hub import InferenceClient
 from langchain_community.llms import Ollama
 
 # Initialize an instance of the Ollama model
-llm = Ollama(model="qwen2")
-# Invoke the model to generate responses
-response = llm.invoke("ما هو حكم القتل العمد في الاسلام ؟  ")
-print(response)
+
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+client = InferenceClient("meta-llama/Llama-3.2-1B")
 
 
 def respond(