turing-motors/Heron-NVILA-Lite-33B

# I have confirmed that 4.46.0 and 4.49.0 also work. Other versions of Transformer may also work, but I have not tested them.
pip install transformers==4.45.0 accelerate opencv-python torchvision einops pillow
pip install git+https://github.com/bfshi/scaling_on_scales.git

from transformers import AutoConfig, AutoModel

model_path = "turing-motors/Heron-NVILA-Lite-33B"

# you can use config
config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
model = AutoModel.from_config(config, trust_remote_code=True, device_map="auto")

# or directly from_pretrained
model = AutoModel.from_pretrained(model_path, trust_remote_code=True, device_map="auto")

# show chat_template
print(model.tokenizer.chat_template)

# examples generate with raw text
response = model.generate_content(["こんにちは"])
print(response)
print("---" * 40)

# examples generate with text + image
from PIL import Image
import requests
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")
response = model.generate_content([image, "画像を説明してください。"])
print(response)
print("---" * 40)

# examples generate using generation_config
from PIL import Image
import requests
from transformers import GenerationConfig
generation_config = {
    "max_new_tokens": 512,
    "temperature": 0.5,
    "do_sample": True,
}
generation_config = GenerationConfig(**generation_config)
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")
response = model.generate_content(
    [image, "画像を説明してください。"],
    generation_config=generation_config
)
print(response)
print("---" * 40)

# examples generate with text + image + text + image + text
from PIL import Image
import requests
url_list = [
    "https://images.unsplash.com/photo-1694831404826-3400c48c188d?q=80&w=2070&auto=format&fit=crop&ixlib=rb-4.0.3&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D",
    "https://images.unsplash.com/photo-1693240876439-473af88b4ed7?q=80&w=1974&auto=format&fit=crop&ixlib=rb-4.0.3&ixid=M3wxMjA3fDB8MHxwaG90by1wYWdlfHx8fGVufDB8fHx8fA%3D%3D"
]
images = [
   Image.open(requests.get(url, stream=True).raw).convert("RGB") for url in url_list
]
response = model.generate_content([
    images[0],
    "これは日本の画像です",
    images[1],
    "これはオーストリアの画像です",
    "各画像の違いを説明して"])
print(response)
print("---" * 40)