diff --git a/README.md b/README.md
index 0db691a8..a2e7d44c 100644
--- a/README.md
+++ b/README.md
@@ -128,7 +128,9 @@ prompt = f"<image>User:{ict_first_instruction} GPT: <answer>{ict_first_response}
 For more details, please refer to our [paper](https://arxiv.org/abs/2306.05425)'s appendix for other tasks.
 ## 🗂️ Environments
 
-You may install via `conda env create -f environment.yml`. Especially to make sure the `transformers>=4.28.0`, `accelerate>=0.18.0`.
+1. Compare cuda version returned by nvidia-smi and nvcc --version. They need to match. Or at least, the version get by nvcc --version should be <= the version get by nvidia-smi.
+2. Install the pytorch that matches your cuda version. (e.g. cuda 11.7 torch 2.0.0). We have successfully run this code on cuda 11.1 torch 1.10.1 and cuda 11.7 torch 2.0.0. Version compatible reference:[here](https://pytorch.org/) or [here](https://pytorch.org/get-started/previous-versions/).
+3. You may install via `conda env create -f environment.yml`. Especially to make sure the `transformers>=4.28.0`, `accelerate>=0.18.0`.
 
 ## 🤗 Hugging Face Model
 
diff --git a/requirements.txt b/requirements.txt
index ec67e8e3..a6398f36 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -15,14 +15,11 @@ numpy>=1.23.5
 open_clip_torch>=2.16.0
 opencv_python_headless>=4.5.5.64
 Pillow>=9.5.0
-Pillow>=9.5.0
 pycocoevalcap>=1.
 pycocotools>=2.0.6
 Requests>=2.31.0
 scipy>=1.10.1
 timm>=0.9.2
-torch>=2.0.0
-torchvision>=0.15.1
 tqdm>=4.65.0
 transformers>=4.29.0
 uvicorn>=0.22.0