diff --git a/docs/swin_guide.md b/docs/swin_guide.md
index a96c9a15d..3bf5ba766 100644
--- a/docs/swin_guide.md
+++ b/docs/swin_guide.md
@@ -219,10 +219,10 @@ pip install timm==0.4.12
 pip install termcolor==1.1.0
 
 bash -x run_test_v1_int8.sh <batch_size> ##profile of swin-v1 INT8 model
-bash -x run_test_v1_int8_accuracy.sh <batch_size> ##test accuracy of swin-v1 INT8 model
+bash -x run_test_v1_int8_accuracy.sh <imagenet-path> ##test accuracy of swin-v1 INT8 model
 
 bash -x run_test_v2_int8.sh <batch_size> ##profile of swin-v2 INT8 model
-bash -x run_test_v2_int8_accuracy.sh <batch_size> ##test accuracy of swin-v2 INT8 model
+bash -x run_test_v2_int8_accuracy.sh <imagenet-path> ##test accuracy of swin-v2 INT8 model
 ```
 Note: When testing PTQ accuracy for INT8 swin-v1-LARGE, we have to specify `--int8-mode 2` instead of `--int8-mode 1` in **run_test_int8.sh**.
 
@@ -517,4 +517,4 @@ On chips with Ampere architectures (like A30, A100), user can use `export NVIDIA
 | BASE  |     16      |    256     | 19.27 | 14.97  |  1.29   |
 | BASE  |     24      |    384     |   -   | 135.38 |    -    |
 | LARGE |     16      |    256     | 31.37 | 24.20  |  1.30   |
-| LARGE |     24      |    384     |   -   |   -    |    -    |
\ No newline at end of file
+| LARGE |     24      |    384     |   -   |   -    |    -    |
diff --git a/examples/pytorch/swin/Swin-Transformer-Quantization/README.md b/examples/pytorch/swin/Swin-Transformer-Quantization/README.md
index 4679cb9fb..657f37af4 100644
--- a/examples/pytorch/swin/Swin-Transformer-Quantization/README.md
+++ b/examples/pytorch/swin/Swin-Transformer-Quantization/README.md
@@ -172,7 +172,7 @@ For example, to evaluate the `Swin-T` with a single GPU. You can see **run.sh**
 python -m torch.distributed.launch --nproc_per_node 1 \
   --master_port 12345 main.py \
   --eval \
-  --cfg SwinTransformer/configs/swin_tiny_patch4_window7_224.yaml \
+  --cfg SwinTransformer/configs/swin/swin_tiny_patch4_window7_224.yaml \
   --resume ./calib-checkpoint/swin_tiny_patch4_window7_224_calib.pth \
   --data-path <imagenet-path> \
   --int8-mode 1\
@@ -214,4 +214,4 @@ python -m torch.distributed.launch --nproc_per_node 4 \
     --batch-size 128 \
     --num-epochs 5 \
     --qat-lr 1e-5
-```
\ No newline at end of file
+```
diff --git a/examples/pytorch/swin/SwinTransformerWeightTransposeQKVWeight.py b/examples/pytorch/swin/SwinTransformerWeightTransposeQKVWeight.py
index 1319e2600..97f34fe51 100644
--- a/examples/pytorch/swin/SwinTransformerWeightTransposeQKVWeight.py
+++ b/examples/pytorch/swin/SwinTransformerWeightTransposeQKVWeight.py
@@ -146,7 +146,9 @@ def __init__(self, layer_num, window_size, depths, num_heads, ths_path, weights=
                     if version == 2:
                         logit_scale_name = 'layers.{}.blocks.{}.attn.logit_scale'.format(layer_idx, block_idx)
                         if logit_scale_name in weights:
-                            self.weights.append(torch.clamp(weights[logit_scale_name], max=torch.log(torch.tensor(1. / 0.01))).exp())
+                            device = weights[logit_scale_name].device
+                            max_value = torch.log(torch.tensor(1. / 0.01)).to(device)
+                            self.weights.append(torch.clamp(weights[logit_scale_name], max=max_value).exp())
                         else:
                             print("[ERROR][SwinTransformerWeights::__init__] missing weight {}.".format(logit_scale_name))
                             exit(-1)