Update app.py

app.py

@@ -13,7 +13,7 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
     trust_remote_code=True,
-    torch_dtype=torch.bfloat16
+    torch_dtype=torch.float32
 ).to(device)
 
 embedding_layer = model.get_input_embeddings()