Update app.py

app.py

@@ -4,7 +4,9 @@ from huggingface_hub import InferenceClient
 """
 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("HuggingFaceTB/SmolLM-135M-Instruct")
+from transformers import pipeline
+
+pipe = pipeline("text-generation", model="HuggingFaceTB/SmolLM-135M-Instruct")
 
 
 def respond(
@@ -26,18 +28,9 @@ def respond(
     messages.append({"role": "user", "content": message})
 
     response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+    for msg in pipe(messages, max_tokens=max_tokens, temperature=temperature, top_p=top_p):
+        yield msg['generated_text']
+    
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface