diff --git a/INSTALLATION.md b/INSTALLATION.md
index 91f22179..efba340b 100644
--- a/INSTALLATION.md
+++ b/INSTALLATION.md
@@ -26,7 +26,8 @@ The **Pytorch-Wildlife** library allows users to directly load the MegadetectorV
 1. Python 3.8 
 2. NVIDIA GPU for CUDA support (Optional, the code and demo also supports cpu calculation).
 3. `conda` or `mamba` for python environment management and specific version of `opencv`.
-4. If you are using CUDA. [CudaToolkit 11.3](https://developer.nvidia.com/cuda-11.3.0-download-archive) is required.
+4. If you are using CUDA. [CudaToolkit 12.1](https://developer.nvidia.com/cuda-12-1-0-download-archive) is required.
+4.1 If you are using CUDA and you have PytorchWildlife 1.0.2.14 or lower, [CudaToolkit 11.3](https://developer.nvidia.com/cuda-11.3.0-download-archive) is required.
 
 ### Create environment
 If you have `conda` or `mamba` installed, you can create a new environment with the following commands (switch `conda` to `mamba` for `mamba` users):
@@ -52,6 +53,14 @@ brew install ffmpeg
 ### Windows
 Windows installation is a bit more complicated due to operating system differences. Please refer to our [Windows installation guide](assets/PytorchWildlife_Windows_installation_tutorial.pdf) for details.
 
+### CUDA for Windows
+If you want to use your CUDA-compatible GPU and you are using Windows. Please run the following commands (CUDA 12.1 is required):
+
+```bash
+pip uninstall torch torchvision torchaudio
+pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
+```
+
 ## Installation
 
 ### Install through pip:
diff --git a/README.md b/README.md
index f0339f12..4cf514b9 100644
--- a/README.md
+++ b/README.md
@@ -18,6 +18,9 @@
 
 
 ## 📣 Announcement
+### Compatibility with CUDA 12.1
+The new version of PytorchWildlife uses the latest version of Pytorch (currently 2.3.1), which is compatible with CUDA 12! 
+
 ### 🥳 MegaDetectorV6 beta testing!
 Greetings! For the past few weeks, we have been working on the next generation of MegaDetector, focusing on computational efficiency and performance. We have trained multiple new models using the latest YOLO-v9 architecture and want to start a public beta testing with these new models to ensure they work as expected on real-world datasets. In the beta testing, we will let people test the compact version of MegaDetectorV6 (MDv6-c). This MDv6-c model has only one-sixth of the parameters of the current MegaDetectorV5 and exhibits 12% higher recall on animal detection in our validation datasets. In other words, MDv6-c has significantly fewer false negatives when detecting animals, making it a more robust model than MegaDetectorV5. 
 
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 00000000..7e0ef953
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,9 @@
+torch
+torchvision
+torchaudio
+tqdm
+Pillow
+supervision==0.16.0
+gradio
+ultralytics-yolov5
+chardet
\ No newline at end of file
diff --git a/setup.py b/setup.py
index 06d1171f..3a2251fc 100644
--- a/setup.py
+++ b/setup.py
@@ -4,7 +4,7 @@
         long_description = file.read()
 setup(
     name='PytorchWildlife',
-    version='1.0.2.14', 
+    version='1.0.2.15', 
     packages=find_packages(),
     url='https://github.com/microsoft/CameraTraps/',  
     license='MIT',
@@ -15,11 +15,11 @@
     long_description_content_type='text/markdown',
     install_requires=[
         'numpy',
-        'torch==1.10.1',
-        'torchvision==0.11.2',
-        'torchaudio==0.10.1',
-        'tqdm==4.66.1',
-        'Pillow==10.1.0', 
+        'torch',
+        'torchvision',
+        'torchaudio',
+        'tqdm',
+        'Pillow', 
         'supervision==0.16.0',
         'gradio',
         'ultralytics-yolov5',
diff --git a/version.txt b/version.txt
index 7fc51196..ff24d869 100644
--- a/version.txt
+++ b/version.txt
@@ -1 +1 @@
-1.0.2.14
\ No newline at end of file
+1.0.2.15
\ No newline at end of file