Hugging Face's logo

NCSOFT
/
VARCO-VISION-2.0-14B

Image-Text-to-Text
Transformers
Safetensors
English
Korean
llava_onevision
image-to-text
multimodal
conversational
ncsoft
ncai
varco
Model card Files Community
3

VARCO-VISION-2.0-14B

Introduction

VARCO-VISION-2.0 is a multimodal AI model capable of understanding both images and text to answer user queries. It supports multi-image inputs, enabling effective processing of complex content such as documents, tables, and charts. The model demonstrates strong comprehension in both Korean and English, with significantly improved text generation capabilities and a deeper understanding of Korean cultural context. Compared to its predecessor, performance has been notably enhanced across various benchmarks, and its usability in real-world scenariosโ€”such as everyday Q&A and information summarizationโ€”has also improved.

In addition to the 14B full-scale model, a lightweight 1.7B version is available for on-device use, making it accessible on personal devices such as smartphones and PCs. VARCO-VISION-2.0 is a powerful open-source AI model built for Korean users and is freely available for a wide range of applications.

๐ŸšจNews๐ŸŽ™๏ธ

  • ๐Ÿ‘€ We are going to release VARCO-VISION-2.0-1.7B-OCR soon!
  • ๐Ÿ‘€ We are going to release VARCO-VISION-2.0-1.7B soon!
  • ๐Ÿ“ฐ 2025-07-18: Updated the checkpoint of VARCO-VISION-2.0-14B for improved performance.
  • ๐Ÿ“ฐ 2025-07-16: We released VARCO-VISION-2.0-14B at link
  • ๐Ÿ“ฐ 2025-07-16: We released GME-VARCO-VISION-Embedding at link

Key Features

  • Multi-image Understanding: Newly added support for multi-image inputs enables the model to analyze multiple images simultaneously and make more holistic and context-aware decisions.
  • Korean Language Specialization: The model is further specialized for Korean, with a deeper understanding of Korean language, context, and culture. Korean text generation has been significantly improved, resulting in more natural, fluent, and accurate responses.
  • OCR with Text Localization: Unlike typical models that only recognize and generate text from images, VARCO-VISION-2.0 can also identify the position of the text and provide bounding boxes around it. This makes it especially useful for document understanding, signage interpretation, and structured visual data.
  • Enhanced Safety: Improved robustness and filtering to ensure safer handling of harmful or sexually explicit content.

VARCO-VISION-2.0 Family

Model Name Base Models (Vision / Language) HF Link
VARCO-VISION-2.0-14B siglip2-so400m-patch16-384 / Qwen3-14B link
VARCO-VISION-2.0-1.7B siglip2-so400m-patch16-384 / Qwen3-1.7B link
VARCO-VISION-2.0-1.7B-OCR siglip2-so400m-patch16-384 / Qwen3-1.7B link
GME-VARCO-VISION-Embedding Qwen2-VL-7B-Instruct link

Model Architecture

VARCO-VISION-2.0 follows the architecture of LLaVA-OneVision.

Evaluation

We adopted benchmark scores directly from OpenVLM Leaderboard where available, and conducted our own evaluations for benchmarks not included in OpenVLM Leaderboard, comparing results against various open-source models to provide a fair and comprehensive evaluation. Please note that for certain benchmarks involving LLM-based evaluation (e.g., LLaVABench), results may not be exactly reproducible due to variations in the underlying LLM behavior.

English Benchmark

Benchmark InternVL3-14B Ovis2-16B Qwen2.5-VL-7B VARCO-VISION-2.0-14B
MMStar 68.9 67.2 64.1 66.5
SEEDBench_IMG 77.5 77.7 77.0 77.7
LLaVABench 84.4 93.0 91.0 88.0
OCRBench 877 879 888 860

Korean Benchmark

Benchmark InternVL3-14B Ovis2-16B Qwen2.5-VL-7B VARCO-VISION-2.0-14B
K-MMStar 64.9 29.7 49.3 63.6
K-SEED 78.2 73.2 75.7 77.2
K-LLaVABench 80.9 86.3 94.1 96.5
K-DTCBench 87.9 81.7 82.1 78.3

Korean Cultural Benchmark

Benchmark InternVL3-14B Ovis2-16B Qwen2.5-VL-7B VARCO-VISION-2.0-14B
K-Viscuit 71.7 77.0 70.9 73.7
PangeaBench (ko) 77.2 76.9 76.6 74.5

Text-only Benchmark

Benchmark InternVL3-14B Ovis2-16B Qwen2.5-VL-7B VARCO-VISION-2.0-14B
MMLU 78.5 78.4 4.6 77.9
MT-Bench 8.93 8.59 8.07 8.98
KMMLU 51.4 49.3 39.6 57.5
KoMT-Bench 7.01 7.91 6.84 7.83
LogicKor 7.00 7.94 6.55 7.40

Note: Some models show unusually low performance on the MMLU benchmark. This is primarily due to their failure to correctly follow the expected output format when only few-shot exemplars are provided in the prompts. Please take this into consideration when interpreting the results.

OCR Benchmark

Benchmark PaddleOCR EasyOCR VARCO-VISION-2.0-14B
CORD 91.4 77.8 93.1
ICDAR2013 92.0 85.0 93.2
ICDAR2015 73.7 57.9 82.4

Usage

To use this model, we recommend installing transformers version 4.53.1 or higher. While it may work with earlier versions, using 4.53.1 or above is strongly recommended, especially to ensure optimal performance for the multi-image feature.

The basic usage is identical to LLaVA-OneVision:

import torch
from transformers import AutoProcessor, LlavaOnevisionForConditionalGeneration

model_name = "NCSOFT/VARCO-VISION-2.0-14B"
model = LlavaOnevisionForConditionalGeneration.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    attn_implementation="sdpa",
    device_map="auto",
)
processor = AutoProcessor.from_pretrained(model_name)

conversation = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/NCSOFT/VARCO-VISION-2.0-14B/resolve/main/demo.jpg"},
            {"type": "text", "text": "์ด ์ด๋ฏธ์ง€์— ํ‘œ์‹œ๋œ ๊ฒƒ์€ ๋ฌด์—‡์ธ๊ฐ€์š”?"},
        ],
    },
]

inputs = processor.apply_chat_template(
    conversation,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt"
).to(model.device, torch.float16)

generate_ids = model.generate(**inputs, max_new_tokens=1024)
generate_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generate_ids)
]
output = processor.decode(generate_ids_trimmed[0], skip_special_tokens=True)
print(output)
Multi image inference 
conversation = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": "file:///path/to/image1.jpg"},
            {"type": "image", "image": "file:///path/to/image2.jpg"},
            {"type": "text", "text": "์ด๋ฏธ์ง€ ๊ฐ„์˜ ์œ ์‚ฌ์ ์„ ํŒŒ์•…ํ•˜์„ธ์š”."},
        ],
    },
]

inputs = processor.apply_chat_template(
    conversation,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt"
).to(model.device, torch.float16)

generate_ids = model.generate(**inputs, max_new_tokens=1024)
generate_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generate_ids)
]
output = processor.decode(generate_ids_trimmed[0], skip_special_tokens=True)
print(output)
OCR inference 
from PIL import Image

image = Image.open("file:///path/to/image.jpg")

# Image upscaling for OCR performance boost
w, h = image.size
target_size = 2304
if max(w, h) < target_size:
    scaling_factor = target_size / max(w, h)
    new_w = int(w * scaling_factor)
    new_h = int(h * scaling_factor)
    image = image.resize((new_w, new_h))

conversation = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": image},
            {"type": "text", "text": "<ocr>"},
        ],
    },
]

inputs = processor.apply_chat_template(
    conversation,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt"
).to(model.device, torch.float16)

generate_ids = model.generate(**inputs, max_new_tokens=1024)
generate_ids_trimmed = [
    out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generate_ids)
]
output = processor.decode(generate_ids_trimmed[0], skip_special_tokens=False)
print(output)
Downloads last month
2,212
Safetensors
Model size
15.2B params
Tensor type
F16
ยท
Inference Providers NEW
Image-Text-to-Text
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for NCSOFT/VARCO-VISION-2.0-14B

Base model

Qwen/Qwen3-14B-Base
Finetuned
Qwen/Qwen3-14B
Finetuned
(71)
this model