Instructions to use open-world-agents/Generalist-IDM-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use open-world-agents/Generalist-IDM-1B with Transformers:

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

pipe = pipeline("image-text-to-text", model="open-world-agents/Generalist-IDM-1B")
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("open-world-agents/Generalist-IDM-1B")
model = AutoModelForMultimodalLM.from_pretrained("open-world-agents/Generalist-IDM-1B")
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 open-world-agents/Generalist-IDM-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "open-world-agents/Generalist-IDM-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "open-world-agents/Generalist-IDM-1B",
		"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/open-world-agents/Generalist-IDM-1B

SGLang

How to use open-world-agents/Generalist-IDM-1B 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 "open-world-agents/Generalist-IDM-1B" \
    --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": "open-world-agents/Generalist-IDM-1B",
		"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 "open-world-agents/Generalist-IDM-1B" \
        --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": "open-world-agents/Generalist-IDM-1B",
		"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 open-world-agents/Generalist-IDM-1B with Docker Model Runner:
```
docker model run hf.co/open-world-agents/Generalist-IDM-1B
```

Update model card for D2E: Add metadata, links, image, and sample usage

by nielsr HF Staff - opened Dec 19, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+139

-3

nielsr

Dec 19, 2025

This PR significantly improves the model card for the D2E model by:

Adding pipeline_tag: robotics to categorize the model accurately, as it focuses on embodied AI and robotics tasks.
Including library_name: transformers to enable the "how to use" widget, as evidenced by the sample code in the GitHub README.
Providing a link to the official paper: D2E: Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI.
Adding a link to the project page: https://worv-ai.github.io/d2e/.
Including a link to the GitHub repository: https://github.com/worv-ai/D2E.
Adding an illustrative image from the GitHub README.
Adding a detailed sample usage code snippet directly from the GitHub README for easy replication.

Please review and merge this PR.

Update model card for D2E: Add metadata, links, image, and sample usage36438ccb

lastdefiance20

open-world-agents org Dec 19, 2025

Hi! Thanks for the PR. This Generalist IDM operates differently from a standard Hub VLM model, so it cannot run without our custom inference code. We are planning to publish a model card, the inference code, and an HF Space demo next week. I’ll keep it in mind for your suggestion when writing the model card.

nielsr

Dec 22, 2025

Thanks! Would be great to add the paper link and metadata tags

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Cannot merge

This branch has merge conflicts in the following files:

README.md

· Sign up or log in to comment