Update app.py

app.py

@@ -36,13 +36,12 @@ parser.add_argument("--port", type=int, default=7860)
 args = parser.parse_args()
 device = args.device
 
-# Load model and tokenizer
-model_path = './iic/mPLUG-Owl3-7B-240728'
+# Replace the model loading section with:
 model = AutoModel.from_pretrained(
     model_path,
     trust_remote_code=True,
     torch_dtype=torch.bfloat16 if 'int4' not in model_path else torch.float32,
-    attn_implementation="flash_attention_2" if device == 'cuda' else None
+    attn_implementation="sdpa"  # Use scaled dot-product attention instead of flash-attn
 ).to(device)
 
 tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)