Instructions to use MBZUAI/OpenEarthAgent with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MBZUAI/OpenEarthAgent with Transformers:

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

pipe = pipeline("text-generation", model="MBZUAI/OpenEarthAgent")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MBZUAI/OpenEarthAgent")
model = AutoModelForCausalLM.from_pretrained("MBZUAI/OpenEarthAgent")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MBZUAI/OpenEarthAgent with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MBZUAI/OpenEarthAgent"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MBZUAI/OpenEarthAgent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MBZUAI/OpenEarthAgent

SGLang

How to use MBZUAI/OpenEarthAgent 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 "MBZUAI/OpenEarthAgent" \
    --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": "MBZUAI/OpenEarthAgent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "MBZUAI/OpenEarthAgent" \
        --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": "MBZUAI/OpenEarthAgent",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MBZUAI/OpenEarthAgent with Docker Model Runner:
```
docker model run hf.co/MBZUAI/OpenEarthAgent
```

AkashahS commited on Feb 19

Commit

ec9a8ba

verified ·

1 Parent(s): 07037f1

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -4

README.md CHANGED Viewed

@@ -5,18 +5,17 @@ language:
 - en
 ---
-## 📝 Description
-<!-- Provide a quick summary of what the model is/does. -->
 ## Model Details
-### Model Description
 OpenEarthAgent is a model trained to perform structured, multi-step reasoning over satellite imagery and GIS data. Designed for remote sensing applications, it integrates multispectral analysis, geospatial operations, and natural-language understanding to enable interpretable, tool-driven decision making.
-## 📚 Additional Resources
 - **Paper:** [ArXiv](https://arxiv.org/abs/2501.13925).
 - **GitHub Repository:** For training and updates: [GitHub - OpenEarthAgent](https://github.com/mbzuai-oryx/OpenEarthAgent).
 - **Project Page:** For a detailed overview, visit our [Project Page - OpenEarthAgent](https://mbzuai-oryx.github.io/OpenEarthAgent/).

 - en
 ---
 ## Model Details
+### 📝 Description
 OpenEarthAgent is a model trained to perform structured, multi-step reasoning over satellite imagery and GIS data. Designed for remote sensing applications, it integrates multispectral analysis, geospatial operations, and natural-language understanding to enable interpretable, tool-driven decision making.
+### 📚 Additional Resources
 - **Paper:** [ArXiv](https://arxiv.org/abs/2501.13925).
 - **GitHub Repository:** For training and updates: [GitHub - OpenEarthAgent](https://github.com/mbzuai-oryx/OpenEarthAgent).
 - **Project Page:** For a detailed overview, visit our [Project Page - OpenEarthAgent](https://mbzuai-oryx.github.io/OpenEarthAgent/).