Upload folder using huggingface_hub

README.md

@@ -66,32 +66,47 @@ pip install -U huggingface_hub
 huggingface-cli download nvidia/EGM-8B --local-dir ./models/EGM-8B
 ```
 
-### Evaluation
+### Inference with SGLang
 
-```bash
-pip install sglang==0.5.5
+Launch the server:
 
-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}"
+```bash
+pip install "sglang[all]>=0.5.5"
 
-cd verl
-bash scripts/sglang_infer.sh
+python -m sglang.launch_server \
+    --model-path nvidia/EGM-8B \
+    --chat-template=qwen3-vl \
+    --port 30000
 ```
 
-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
+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