Update app.py

app.py

@@ -1,8 +1,8 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import pipeline
 
-
-client = InferenceClient("daniel-dona/google-gemma-3-270m")
+model = "daniel-dona/google-gemma-3-270m-it"
+pipe = pipeline("text-generation", model=model)
 
 
 def respond(
@@ -25,19 +25,17 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
+    response = pipe(
         messages,
-        max_tokens=max_tokens,
-        stream=True,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+        return_full_text=False, 
+    )
+
+    generated_text = response[0]['generated_text']
 
-        response += token
-        yield response
+    yield generated_text
 
 
 """