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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("zmli/G-Substrate-Qwen3-VL-2B")
model = AutoModelForMultimodalLM.from_pretrained("zmli/G-Substrate-Qwen3-VL-2B", device_map="auto")
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 Settings

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
```

Improve metadata and model card

by nielsr HF Staff - opened May 27

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+16

-18

Files changed (1) hide show

README.md +16 -18

README.md CHANGED Viewed

@@ -1,23 +1,26 @@
 ---
-license: apache-2.0
 base_model: Qwen/Qwen3-VL-2B-Instruct
 tags:
-  - graph
-  - multi-task
-  - multi-modal
-  - scene-graph
-  - event-graph
-  - molecular-graph
-pipeline_tag: text-generation
 ---
 # G-Substrate (Qwen3-VL-2B)
 Multi-task fine-tuned model from the paper **"Graph is a Substrate Across Data Modalities"** (ICML 2026).
 ## Model Description
-This model is fine-tuned from [Qwen3-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct) using the G-Substrate framework, which organizes learning around shared graph structures across heterogeneous modalities and tasks.
 ### Training Details
@@ -43,11 +46,11 @@ This model is fine-tuned from [Qwen3-VL-2B-Instruct](https://huggingface.co/Qwen
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-model = AutoModelForCausalLM.from_pretrained("path/to/G-Substrate-Qwen3-VL-2B", trust_remote_code=True)
-tokenizer = AutoTokenizer.from_pretrained("path/to/G-Substrate-Qwen3-VL-2B", trust_remote_code=True)
 ```
-For batch inference with vLLM, see the [G-Substrate repository](https://github.com/TODO).
 ## Results
@@ -55,11 +58,6 @@ For batch inference with vLLM, see the [G-Substrate repository](https://github.c
 |----:|----:|----:|----:|-------:|--------:|----------:|--------:|--------:|--------:|-------:|
 | 98.41 | 96.97 | 48.59 | 94.54 | 51.53 | 68.47 | 25.38 | 52.20 | 42.68 | 40.91 | 25.15 |
-## Links
-- Code: [zmli6/G-Substrate](https://github.com/zmli6/G-Substrate)
-- Dataset: [zmli/G-Substrate-Data](https://huggingface.co/datasets/zmli/G-Substrate-Data)
 ## Citation
 ```bibtex
@@ -69,4 +67,4 @@ For batch inference with vLLM, see the [G-Substrate repository](https://github.c
   booktitle={ICML},
   year={2026}
 }
-```

 ---
 base_model: Qwen/Qwen3-VL-2B-Instruct
+license: apache-2.0
+pipeline_tag: image-text-to-text
+library_name: transformers
 tags:
+- graph
+- multi-task
+- multi-modal
+- scene-graph
+- event-graph
+- molecular-graph
 ---
 # G-Substrate (Qwen3-VL-2B)
 Multi-task fine-tuned model from the paper **"Graph is a Substrate Across Data Modalities"** (ICML 2026).
+[[Paper](https://huggingface.co/papers/2601.22384)] [[Code](https://github.com/zmli6/G-Substrate)] [[Dataset](https://huggingface.co/datasets/zmli/G-Substrate-Data)]
 ## Model Description
+This model is fine-tuned from [Qwen3-VL-2B-Instruct](https://huggingface.co/Qwen/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
 ```python
 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](https://github.com/zmli6/G-Substrate).
 ## Results
 |----:|----:|----:|----:|-------:|--------:|----------:|--------:|--------:|--------:|-------:|
 | 98.41 | 96.97 | 48.59 | 94.54 | 51.53 | 68.47 | 25.38 | 52.20 | 42.68 | 40.91 | 25.15 |
 ## Citation
 ```bibtex
   booktitle={ICML},
   year={2026}
 }
+```