docs: add numpy issue to troubleshooting

fern/docs/pages/installation/installation.mdx

@@ -248,6 +248,9 @@ In order for local LLM and embeddings to work, you need to download the models t
 poetry run python scripts/setup
 ```
 
+If you want to run PrivateGPT with Llama-CPP running using CUDA, please follow the instructions in the
+[troubleshooting](#/installation/getting-started/troubleshooting#guide-for-building-llama-cpp-with-cuda-support) section.
+
 Once installed, you can run PrivateGPT with the following command:
 
 ```bash

fern/docs/pages/installation/troubleshooting.mdx

@@ -46,4 +46,31 @@ huggingface:
 embedding:
   embed_dim: 384
 ```
-</Callout>
+</Callout>
+
+# Guide for Building llama-cpp with CUDA support
+
+## Numpy installation issue
+
+First, ensure you have the necessary prerequisites installed on your system.
+You'll need to force a specific version of NumPy due to compatibility issues.
+Run the following command to install `llama-cpp` with CUDA support:
+
+```bash
+CMAKE_ARGS='-DLLAMA_CUBLAS=on' poetry run pip install --force-reinstall --no-cache-dir llama-cpp-python numpy==1.26.0
+```
+
+Give thanks to [MarioRossiGithub](https://github.com/MarioRossiGithub) for providing the following solution.
+
+## Out-of-memory error
+
+If you encounter an out-of-memory error while running `llama-cpp` with CUDA, you can try the following steps to resolve the issue:
+1. **Set the next environment:**
+    ```bash
+    TOKENIZERS_PARALLELISM=true
+    ```
+2. **Run PrivateGPT:**
+    ```bash
+    poetry run python -m privategpt
+    ```
+Give thanks to [MarioRossiGithub](https://github.com/MarioRossiGithub) for providing the following solution.