Instructions to use zmli/G-Substrate-Qwen3-VL-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zmli/G-Substrate-Qwen3-VL-2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="zmli/G-Substrate-Qwen3-VL-2B")
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 AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("zmli/G-Substrate-Qwen3-VL-2B")
model = AutoModelForImageTextToText.from_pretrained("zmli/G-Substrate-Qwen3-VL-2B")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use zmli/G-Substrate-Qwen3-VL-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zmli/G-Substrate-Qwen3-VL-2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zmli/G-Substrate-Qwen3-VL-2B",
		"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/zmli/G-Substrate-Qwen3-VL-2B

SGLang

How to use zmli/G-Substrate-Qwen3-VL-2B 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 "zmli/G-Substrate-Qwen3-VL-2B" \
    --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": "zmli/G-Substrate-Qwen3-VL-2B",
		"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 "zmli/G-Substrate-Qwen3-VL-2B" \
        --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": "zmli/G-Substrate-Qwen3-VL-2B",
		"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 zmli/G-Substrate-Qwen3-VL-2B with Docker Model Runner:
```
docker model run hf.co/zmli/G-Substrate-Qwen3-VL-2B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

G-Substrate (Qwen3-VL-2B)

Multi-task fine-tuned model from the paper "Graph is a Substrate Across Data Modalities" (ICML 2026).

[Paper] [Code] [Dataset]

Model Description

This model is fine-tuned from Qwen3-VL-2B-Instruct using the G-Substrate framework. G-Substrate treats graph structure as a persistent structural substrate that accumulates knowledge across heterogeneous data modalities and tasks. It employs a unified structural schema for compatibility and an interleaved role-based training strategy.

Training Details

Base model: Qwen3-VL-2B-Instruct
Training method: Full fine-tuning (SFT) with multi-task learning
Training data: Scene graphs, event graphs, molecular graphs, graph algorithmic tasks, and interleaved role-based data
Epochs: 2
Learning rate: 8e-6 (cosine schedule, warmup 10%)
Batch size: 1 per device, 32 gradient accumulation steps
GPUs: 2x NVIDIA A100 (DeepSpeed ZeRO-3)

Supported Tasks

Task	Domain	Input	Output
Scene Graph Generation	Visual	Image	Graph triplets
Event Relation Extraction	Text	Document + events	Event relation graph
Molecular Graph Description	Scientific	SMILES + graph	Natural language description
Graph Algorithmic Reasoning	Algorithmic	Graph description	Algorithm answer

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("zmli/G-Substrate-Qwen3-VL-2B", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("zmli/G-Substrate-Qwen3-VL-2B", trust_remote_code=True)

For batch inference with vLLM, see the G-Substrate repository.

Results

CT	CD	SP	BM	BLEU-4	ROUGE-L	PCIs R@50	MA-S F1	MA-T F1	MA-C F1	HiE F1
98.41	96.97	48.59	94.54	51.53	68.47	25.38	52.20	42.68	40.91	25.15

Citation

@inproceedings{li2026gsubstrate,
  title={Graph is a Substrate Across Data Modalities},
  author={Li, Ziming and Wu, Xiaoming and Wang, Zehong and Li, Jiazheng and Tian, Yijun and Bi, Jinhe and Ma, Yunpu and Ye, Yanfang and Zhang, Chuxu},
  booktitle={ICML},
  year={2026}
}