Efficient-Large-Model/NVILA-Lite-2B-hf-preview

Dependency setups:

pip install transformers==4.46 accelerate opencv-python torchvision einops 
pip install git+https://github.com/bfshi/scaling_on_scales.git

from transformers import AutoConfig, AutoModel
from termcolor import colored

model_path = "Efficient-Large-Model/NVILA-Lite-2B-hf-preview"

# config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
# model = AutoModel.from_config(config, trust_remote_code=True)
model = AutoModel.from_pretrained(model_path, trust_remote_code=True, device_map="auto")
res = model.generate_content([
    "how are you today?"
])
print(colored(res, "cyan", attrs=["bold"]))

print("---" * 40)

import PIL.Image
response = model.generate_content([
    PIL.Image.open("inference_test/test_data/caption_meat.jpeg"),
    "describe the image?"
])
print(colored(response, "cyan", attrs=["bold"]))