Update app.py

app.py

@@ -28,14 +28,9 @@ assert device in ['cuda', 'mps']
 # Load model
 model_path = 'y0un92/test'
 
-if 'int4' in model_path:
-    if device == 'mps':
-        print('Error: running int4 model with bitsandbytes on Mac is not supported right now.')
-        exit()
-    model = AutoModel.from_pretrained(model_path, trust_remote_code=True)
-else:
-    model = AutoModel.from_pretrained(model_path, trust_remote_code=True).to(dtype=torch.float16)
-    model = model.to(device=device)
+# Load model directly
+from transformers import AutoModel
+model = AutoModel.from_pretrained("y0un92/test", trust_remote_code=True)
 tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
 model.eval()