Update app.py

app.py

@@ -15,8 +15,8 @@ print (pipe(messages1) )
 """
 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(model="google/recurrentgemma-2b-it")
-
+#client = InferenceClient(model="google/recurrentgemma-2b-it")
+client = pipeline("text-generation", model="google/recurrentgemma-2b-it")
 
 def respond(
     message,
@@ -38,7 +38,7 @@ def respond(
 
     response = ""
 
-    for message in client.chat_completion(
+    for message in client(
         messages,
         max_tokens=max_tokens,
         stream=False,