diff --git a/qlib/contrib/model/pytorch_alstm.py b/qlib/contrib/model/pytorch_alstm.py
index cfe629fa8..d85fef628 100644
--- a/qlib/contrib/model/pytorch_alstm.py
+++ b/qlib/contrib/model/pytorch_alstm.py
@@ -76,7 +76,7 @@ class ALSTM(Model):
         self.early_stop = early_stop
         self.optimizer = optimizer.lower()
         self.loss = loss
-        self.device = "cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu"
+        self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu")
         self.use_gpu = torch.cuda.is_available()
         self.seed = seed
 
diff --git a/qlib/contrib/model/pytorch_gats.py b/qlib/contrib/model/pytorch_gats.py
index 1759ae5ba..c22e48204 100644
--- a/qlib/contrib/model/pytorch_gats.py
+++ b/qlib/contrib/model/pytorch_gats.py
@@ -83,7 +83,7 @@ class GATs(Model):
         self.base_model = base_model
         self.with_pretrain = with_pretrain
         self.model_path = model_path
-        self.device = "cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu"
+        self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu")
         self.use_gpu = torch.cuda.is_available()
         self.seed = seed
 
diff --git a/qlib/contrib/model/pytorch_gru.py b/qlib/contrib/model/pytorch_gru.py
index 8d5a9e461..22c63c539 100755
--- a/qlib/contrib/model/pytorch_gru.py
+++ b/qlib/contrib/model/pytorch_gru.py
@@ -76,7 +76,7 @@ class GRU(Model):
         self.early_stop = early_stop
         self.optimizer = optimizer.lower()
         self.loss = loss
-        self.device = "cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu"
+        self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu")
         self.use_gpu = torch.cuda.is_available()
         self.seed = seed
 
diff --git a/qlib/contrib/model/pytorch_lstm.py b/qlib/contrib/model/pytorch_lstm.py
index 8032c54eb..1c24246f8 100755
--- a/qlib/contrib/model/pytorch_lstm.py
+++ b/qlib/contrib/model/pytorch_lstm.py
@@ -76,7 +76,7 @@ class LSTM(Model):
         self.early_stop = early_stop
         self.optimizer = optimizer.lower()
         self.loss = loss
-        self.device = "cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu"
+        self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu")
         self.use_gpu = torch.cuda.is_available()
         self.seed = seed
 
diff --git a/qlib/contrib/model/pytorch_nn.py b/qlib/contrib/model/pytorch_nn.py
index ed4ba8692..2e2a3e885 100644
--- a/qlib/contrib/model/pytorch_nn.py
+++ b/qlib/contrib/model/pytorch_nn.py
@@ -79,7 +79,7 @@ class DNNModelPytorch(Model):
         self.lr_decay_steps = lr_decay_steps
         self.optimizer = optimizer.lower()
         self.loss_type = loss
-        self.device = "cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu"
+        self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu")
         self.use_GPU = torch.cuda.is_available()
         self.seed = seed
 
diff --git a/qlib/contrib/model/pytorch_sfm.py b/qlib/contrib/model/pytorch_sfm.py
index da75b1bca..15d945c89 100644
--- a/qlib/contrib/model/pytorch_sfm.py
+++ b/qlib/contrib/model/pytorch_sfm.py
@@ -239,7 +239,7 @@ class SFM(Model):
         self.eval_steps = eval_steps
         self.optimizer = optimizer.lower()
         self.loss = loss
-        self.device = "cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu"
+        self.device = torch.device("cuda:%d" % (GPU) if torch.cuda.is_available() else "cpu")
         self.use_gpu = torch.cuda.is_available()
         self.seed = seed