Update app.py

app.py

@@ -60,14 +60,14 @@ def predict(message, history, system_prompt, temperature, max_tokens):
 
 if __name__ == "__main__":
     args = parse_args()
-    tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-2-chat", trust_remote_code=True)
-    model = AutoModelForCausalLM.from_pretrained("stabilityai/stablelm-2-chat", trust_remote_code=True, torch_dtype=torch.bfloat16)
+    tokenizer = AutoTokenizer.from_pretrained("stabilityai/stablelm-2-12b-chat", trust_remote_code=True)
+    model = AutoModelForCausalLM.from_pretrained("stabilityai/stablelm-2-12b-chat", trust_remote_code=True, torch_dtype=torch.bfloat16)
     device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
     model = model.to(device)
     gr.ChatInterface(
         predict,
-        title="StableLM 2 Chat - Demo",
-        description="StableLM 2 Chat - StabilityAI",
+        title="StableLM 2 12B Chat - Demo",
+        description="StableLM 2 12B Chat - StabilityAI",
         theme="soft",
         chatbot=gr.Chatbot(label="Chat History",),
         textbox=gr.Textbox(placeholder="input", container=False, scale=7),