Instructions to use Paranioar/NEO1_5-2B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Paranioar/NEO1_5-2B-SFT with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Paranioar/NEO1_5-2B-SFT", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Paranioar/NEO1_5-2B-SFT", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Paranioar/NEO1_5-2B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Paranioar/NEO1_5-2B-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Paranioar/NEO1_5-2B-SFT",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Paranioar/NEO1_5-2B-SFT

SGLang

How to use Paranioar/NEO1_5-2B-SFT with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Paranioar/NEO1_5-2B-SFT" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Paranioar/NEO1_5-2B-SFT",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Paranioar/NEO1_5-2B-SFT" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Paranioar/NEO1_5-2B-SFT",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use Paranioar/NEO1_5-2B-SFT with Docker Model Runner:
```
docker model run hf.co/Paranioar/NEO1_5-2B-SFT
```

From Pixels to Words -- Towards Native One-Vision Models at Scale
| Paper | Code |

🌟🌟 Motivation

Can native VLMs generalize across single-image, multi-image, Video, and 3D spatial scenarios?
What advantages of native VLMs, especially early-fusion for pixel-pixel，pixel-word?
How to build strong native VLMs over Qwen3-VL for subsequent RL community?

🧑‍🎨🧑‍🎨 Model Overview

NEO1_5-2B has the following features:

Model Type: Native Vision-Language Models
Model Mode: Mixed Native-Attn & Native-RoPE
Layer Parameters: 56M vs. 50M (Qwen3-1.7B)
Model Parameters: 2.2B (Non-Embedding)
Number of Layers: 40 (12 for Pre-Buffer & 28 for Post-LLM)
Number of Heads: 16 for Q and 8 for KV (GQA)
Head Dimensions: 128 * 2 for QK and 128 for V

🔥🔥 Model Performance

✒️✒️ Citation

If NEO-ov is helpful for your research, please consider star ⭐ and citation 📝 :

@article{Diao2026NEOov,
  title        = {From Pixels to Words--Towards Native One-Vision Models at Scale},
  author       = {Diao, Haiwen and Wang, Jiahao and Wu, Penghao and Dong, Yuhao and Niu, Yuwei and Zhu, Yue and Cai, Zhongang and Fan, Weichen and Dai, Linjun and Wu, Silei and others},
  journal      = {arXiv preprint arXiv:2605.28820},
  year         = {2026}
}

Downloads last month: 14

Safetensors

Model size

3B params

Tensor type

BF16

Collection including Paranioar/NEO1_5-2B-SFT

NEO1_5

Collection

From Pixels to Words -- Towards Native One-Vision Models at Scale • 3 items • Updated about 12 hours ago • 6

Paper for Paranioar/NEO1_5-2B-SFT

From Pixels to Words -- Towards Native One-Vision Models at Scale

Paper • 2605.28820 • Published 1 day ago • 52

From Pixels to Words -- Towards Native One-Vision Models at Scale | Paper | Code |