Update app.py

app.py

@@ -32,7 +32,7 @@ class ConversationManager:
         try:
             print(f"Attempting to load model: {model_name}")
             tokenizer = AutoTokenizer.from_pretrained(model_name)
-        try:
+        except:
             # Try to load the model with 8-bit quantization
             model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", load_in_8bit=True)
         except RuntimeError as e: