Update app.py

app.py

@@ -6,11 +6,11 @@ from threading import Thread
 import spaces
 
 token = os.environ["HF_TOKEN"]
-model = AutoModelForCausalLM.from_pretrained("google/gemma-2b-it", 
+model = AutoModelForCausalLM.from_pretrained("google/gemma-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-2b-it",token=token)
+tok = AutoTokenizer.from_pretrained("google/gemma-7b-it",token=token)
 # using CUDA for an optimal experience
 # device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 device = torch.device('cuda')
@@ -57,5 +57,5 @@ demo = gr.ChatInterface(fn=chat,
                         chatbot=gr.Chatbot(show_label=True, show_share_button=True, show_copy_button=True, likeable=True, layout="bubble", bubble_full_width=False),
                         theme="Soft",
                         examples=[["Write me a poem about Machine Learning."]], 
-                        title="gemma 2b-it")
-demo.launch()
+                        title="Text Streaming")
+demo.launch()