Update app.py

app.py

@@ -10,7 +10,7 @@ model = AutoModelForCausalLM.from_pretrained("google/gemma-1.1-7b-it",
                                              # torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
                                              torch_dtype=torch.float16,
                                              token=token)
-tok = AutoTokenizer.from_pretrained("google/gemma-1.1-7b-it,token=token)
+tok = AutoTokenizer.from_pretrained("google/gemma-1.1-7b-it",token=token)
 # using CUDA for an optimal experience
 # device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 if torch.cuda.is_available():
@@ -58,5 +58,5 @@ def chat(message, history):
 
 
 
-demo = gr.ChatInterface(fn=chat, examples=[["Write me a poem about Machine Learning."]], title="gemma 2b-it")
+demo = gr.ChatInterface(fn=chat, examples=[["Write me a poem about Machine Learning."]], title="gemma-1.1-7b-it"")
 demo.launch()