Update app.py

app.py

@@ -142,20 +142,16 @@ def chat_with_model(input_sentence):
     
     
     print(apikey)
-    client = OpenAI(
-        api_key = apikey
-    	base_url ="https://api-inference.huggingface.co/v1/",
-    	
-    )
+    from huggingface_hub import InferenceClient
+
+    client = InferenceClient(api_key="YOUR_HF_TOKEN")
 
     messages = [
-        
-    	{ "role": "user", "content": "سلام" },
-    	
+    	{ "role": "user", "content": "Tell me a story" }
     ]
 
     stream = client.chat.completions.create(
-        model="Qwen/Qwen2.5-Coder-32B-Instruct", 
+        model="Qwen/Qwen2.5-72B-Instruct", 
     	messages=messages, 
     	temperature=0.5,
     	max_tokens=2048,
@@ -164,9 +160,8 @@ def chat_with_model(input_sentence):
     )
 
     for chunk in stream:
-        print(chunk.choices[0].delta.content)
-        return (chunk.choices[0].delta.content)
-        
+        print(chunk.choices[0].delta.content)        
+
 # رابط کاربری Gradio  
 with gr.Blocks() as demo:  
     gr.Markdown("## چت با مدل")