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

Libraries

How to use trillionlabs/gWorld-8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="trillionlabs/gWorld-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("trillionlabs/gWorld-8B")
model = AutoModelForImageTextToText.from_pretrained("trillionlabs/gWorld-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 Settings

vLLM

How to use trillionlabs/gWorld-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "trillionlabs/gWorld-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": "trillionlabs/gWorld-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/trillionlabs/gWorld-8B

SGLang

How to use trillionlabs/gWorld-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 "trillionlabs/gWorld-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": "trillionlabs/gWorld-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 "trillionlabs/gWorld-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": "trillionlabs/gWorld-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 trillionlabs/gWorld-8B with Docker Model Runner:
```
docker model run hf.co/trillionlabs/gWorld-8B
```

Improve model card: Add pipeline_tag, library_name, paper link, and sample usage

by nielsr HF Staff - opened Feb 4

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+120

-9

nielsr

Feb 4

Hi! I'm Niels from the Hugging Face community science team. I've opened this PR to enhance your model card's discoverability and usability.

Specifically, I've made the following improvements:

Added pipeline_tag: image-text-to-text to the YAML metadata, which accurately reflects the model's functionality of taking an image and text input to produce text output.
Added library_name: transformers to the metadata, as indicated by the model's configuration and explicit usage of transformers.AutoProcessor in your GitHub README. This enables automated code snippets on the Hub.
Linked the model card to the associated paper Generative Visual Code Mobile World Models on the Hugging Face platform. The existing arXiv link in the quick links has been preserved as per guidelines.
Included a "Sample Usage" section with a Python code snippet for inference using vLLM, directly copied from your official GitHub repository to provide a ready-to-use example for users.
Corrected the formatting of the citation block for better readability.

These updates aim to make your model easier to find and integrate for the community. Please let me know if you have any feedback!

Improve model card: Add pipeline_tag, library_name, paper link, and sample usage710f8742

sungjunhan-trl changed pull request status to merged Feb 4

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

Tap or paste here to upload images

· Sign up or log in to comment