Trying to run huggingface model on virtual machine (ubuntu guest)

Question

I am trying to run model from transformers -> deepseek-ai/DeepSeek-V2-Lite on Ubuntu 22.04.4 LTS as guest with VirtualBox 7.

When i run my test block:

prompt = "how may I help you"
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")  
outputs = model.generate(inputs["input_ids"], max_length=50, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

I get an error:

RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx

From what I have researched I should not install drivers on vm because this might cause issues (confirm please). How to approach this then?

when i run lspci |grep VBA in terminal i get respone 00:02.0 VGA compatible controller: VMware SVGA II Adapter