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

Libraries

How to use zzzrw/GEM-2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="zzzrw/GEM-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, AutoModelForSeq2SeqLM

processor = AutoProcessor.from_pretrained("zzzrw/GEM-2B")
model = AutoModelForSeq2SeqLM.from_pretrained("zzzrw/GEM-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 zzzrw/GEM-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zzzrw/GEM-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": "zzzrw/GEM-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/zzzrw/GEM-2B

SGLang

How to use zzzrw/GEM-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 "zzzrw/GEM-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": "zzzrw/GEM-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 "zzzrw/GEM-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": "zzzrw/GEM-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 zzzrw/GEM-2B with Docker Model Runner:
```
docker model run hf.co/zzzrw/GEM-2B
```

zzzrw commited on Jun 1

Commit

d1a104d

verified ·

1 Parent(s): 8854e3d

Update README.md

Browse files

Files changed (1) hide show

README.md +17 -1

README.md CHANGED Viewed

@@ -8,6 +8,10 @@ language:
 base_model:
 - Qwen/Qwen3-VL-2B-Instruct
 pipeline_tag: image-text-to-text
 ---
 <div align="center">
@@ -48,4 +52,16 @@ Embodied Vision-Language Models (VLMs) have demonstrated impressive performance
 <div align="center">
 <img src="assets/overview.png" alt="GEM Teaser" width="85%">
-</div>

 base_model:
 - Qwen/Qwen3-VL-2B-Instruct
 pipeline_tag: image-text-to-text
+library_name: transformers
+tags:
+- Vision-Language-Model
+- Vision-Language-Action
 ---
 <div align="center">
 <div align="center">
 <img src="assets/overview.png" alt="GEM Teaser" width="85%">
+</div>
+If you find our work helpful, please consider citing:
+```
+@article{zhao2026gem,
+  title={GEM: Generative Supervision Helps Embodied Intelligence},
+  author={Zhao, Ruowen and Li, Bangguo and Liu, Zuyan and Liang, Yinan and Ye, Junliang and Liu, Fangfu and Wu, Diankun and Wang, Zhengyi and Yu, Xumin and Rao, Yongming and others},
+  journal={arXiv preprint arXiv:2605.28548},
+  year={2026}
+}
+```