sudo apt update
sudo apt install pciutils lshw
curl -fsSL https://ollama.com/install.sh | sh

ollama serve

ollama

ollama run gemma3:27b

!pip install torch torchvision torchaudio einops timm pillow
!pip install git+https://github.com/huggingface/[email protected]
!pip install git+https://github.com/huggingface/accelerate
!pip install git+https://github.com/huggingface/diffusers
!pip install huggingface_hub
!pip install sentencepiece bitsandbytes protobuf decord numpy

!huggingface-cli login --token <YOUR_HF_TOKEN>

from transformers import pipeline
import torch
from PIL import Image

pipe = pipeline(
    "image-text-to-text",
    model="google/gemma-3-27b-it",
    device="cuda",
    torch_dtype=torch.bfloat16
)

image = Image.open('./test-image.jpg').convert('RGB')
prompt = "Describe what's in the image in detail"
system_prompt = "You are a helpful assistant."

messages = [
    { "role": "system", "content": [{"type": "text", "text": system_prompt}] },
    { "role": "user", "content": [{"type": "image", "url": image}, {"type": "text", "text": prompt}] }
]

output = pipe(text=messages, max_new_tokens=500)
print(output[0]["generated_text"][-1]["content"])