Heron-NVILA-Lite-2B

[!NOTE] We have released Heron-NVILA-Lite-2B-hf, an implementation compatible with transformers.AutoModelForImageTextToText.

Heron-NVILA-Lite-2B

Heron-NVILA-Lite-2B is a vision language model trained for Japanese, based on the NVILA-Lite architecture.

Model Overview

• Developer: Turing Inc.
• Vision Encoder: paligemma-siglip-so400m-patch14-448
• Projector: mlp_downsample_2x2_fix
• LLM: Qwen2.5-1.5B-Instruct
• Supported Languages: Japanese, English

Setup

# 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

Usage

from transformers import AutoConfig, AutoModel

model_path = "turing-motors/Heron-NVILA-Lite-2B"

# 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)

Training Summary

Evaluation

I used llm-jp-eval-mm for this evaluation. Scores for models other than Heron-NVILA-Lite and Sarashina2-Vision-14B were taken from llm-jp-eval-mm leaderboard as of March 2025 and the Asagi website. Heron-NVILA-Lite and Sarashina2-Vision-14B were evaluated using llm-as-a-judge with "gpt-4o-2024-05-13". Sarashina2-Vision-14B was evaluated on the official blog using "gpt-4o-2024-08-06"; please note that due to differing evaluation conditions, the results for Sarashina2-Vision-14B should be treated as reference only.

Risks and Limitations

This model is experimental and has not been thoroughly calibrated for ethical compliance or legal standards. Caution is advised for sensitive applications.

License

• Model weights are licensed under Apache License 2.0.
• Users must comply with OpenAI terms of use due to the inclusion of GPT-4-generated synthetic data.

Acknowledgements

This model is based on results obtained from a project, JPNP20017, subsidized by the New Energy and Industrial Technology Development Organization (NEDO).

I would like to acknowledge the use of the following open-source repositories:

• VILA
• llm-jp-eval-mm