Update app.py

app.py

@@ -5,27 +5,20 @@ def greet(name):
 
 from huggingface_hub import InferenceClient
 
-client = InferenceClient()
+
+# Use a pipeline as a high-level helper
+from transformers import pipeline
 
 messages = [
-	{
-		"role": "user",
-		"content": "What is the capital of France?"
-	}
+    {"role": "user", "content": "Who are you?"},
 ]
+pipe = pipeline("text-generation", model="meta-llama/Llama-3.1-8B-Instruct")
+pipe(messages)
 
-stream = client.chat.completions.create(
-    model="Qwen/Qwen2.5-Math-7B-Instruct", 
-	messages=messages, 
-	max_tokens=500,
-	stream=True
-)
 
-for chunk in stream:
-    print(chunk.choices[0].delta.content, end="")
 
 
 
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
+#demo = gr.Interface(fn=greet, inputs="text", outputs="text")
+#demo.launch()