You need the UV package/project manager to install the dependencies.
You can get it from here.

Set up the environment. (Only once)

uv venv
.venv/Scripts/activate
uv pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118 --link-mode=symlink
uv sync

Run the script.

.venv/Scripts/activate
uv run python ./deepseek/deepseek_ai.py

Models will be downloaded on the first run.

Models are fetched from HuggingFace.

1. deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
2. deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
3. deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
4. deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
5. deepseek-ai/DeepSeek-R1-Distill-Llama-70B
6. deepseek-ai/DeepSeek-R1-Distill-Llama-8B
7. deepseek-ai/DeepSeek-R1
8. deepseek-ai/DeepSeek-R1-Zero