Instructions to use nvidia/EGM-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/EGM-8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="nvidia/EGM-8B")
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("nvidia/EGM-8B")
model = AutoModelForImageTextToText.from_pretrained("nvidia/EGM-8B")
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 nvidia/EGM-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/EGM-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/EGM-8B",
		"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/nvidia/EGM-8B

SGLang

How to use nvidia/EGM-8B 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 "nvidia/EGM-8B" \
    --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": "nvidia/EGM-8B",
		"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 "nvidia/EGM-8B" \
        --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": "nvidia/EGM-8B",
		"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 nvidia/EGM-8B with Docker Model Runner:
```
docker model run hf.co/nvidia/EGM-8B
```

ligeng-zhu-nv commited on Apr 10

Commit

f5bc2e9

verified ·

1 Parent(s): 85875a0

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

README.md +36 -21

README.md CHANGED Viewed

@@ -66,32 +66,47 @@ pip install -U huggingface_hub
 huggingface-cli download nvidia/EGM-8B --local-dir ./models/EGM-8B
 ```
-### Evaluation
-```bash
-pip install sglang==0.5.5
-export BASE_DIR=$(pwd)
-export MODEL_PATH="${BASE_DIR}/models/EGM-8B"
-export DATA_JSON="${BASE_DIR}/data/EGM_Datasets/metadata/eval/refcoco+_testA.jsonl"
-export OUTPUT_DIR="${BASE_DIR}/result/"
-export BASE_IMG_DIR="${BASE_DIR}"
-cd verl
-bash scripts/sglang_infer.sh
 ```
-vLLM is also supported:
-```bash
-export BASE_DIR=$(pwd)
-export MODEL_PATH="${BASE_DIR}/models/EGM-8B"
-export DATA_JSON="${BASE_DIR}/data/EGM_Datasets/metadata/eval/refcoco+_testA.jsonl"
-export OUTPUT_DIR="${BASE_DIR}/result/"
-export BASE_IMG_DIR="${BASE_DIR}"
-cd verl
-bash scripts/vllm_infer.sh
 ```
 ## Model Architecture

 huggingface-cli download nvidia/EGM-8B --local-dir ./models/EGM-8B
 ```
+### Inference with SGLang
+Launch the server:
+```bash
+pip install "sglang[all]>=0.5.5"
+python -m sglang.launch_server \
+    --model-path nvidia/EGM-8B \
+    --chat-template=qwen3-vl \
+    --port 30000
 ```
+Send a visual grounding request:
+```python
+import openai
+import base64
+client = openai.Client(base_url="http://127.0.0.1:30000/v1", api_key="EMPTY")
+# Load a local image as base64
+with open("example.jpg", "rb") as f:
+    image_base64 = base64.b64encode(f.read()).decode("utf-8")
+response = client.chat.completions.create(
+    model="nvidia/EGM-8B",
+    messages=[
+        {
+            "role": "user",
+            "content": [
+                {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{image_base64}"}},
+                {"type": "text", "text": "Please provide the bounding box coordinate of the region this sentence describes: the person on the left."},
+            ],
+        }
+    ],
+    temperature=0.6,
+    top_p=0.95,
+    max_tokens=8192,
+)
+print(response.choices[0].message.content)
 ```
 ## Model Architecture