Instructions to use tomg-group-umd/zero-model-checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tomg-group-umd/zero-model-checkpoints with Transformers:

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

pipe = pipeline("image-text-to-text", model="tomg-group-umd/zero-model-checkpoints")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tomg-group-umd/zero-model-checkpoints", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tomg-group-umd/zero-model-checkpoints with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tomg-group-umd/zero-model-checkpoints"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tomg-group-umd/zero-model-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tomg-group-umd/zero-model-checkpoints

SGLang

How to use tomg-group-umd/zero-model-checkpoints 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 "tomg-group-umd/zero-model-checkpoints" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tomg-group-umd/zero-model-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "tomg-group-umd/zero-model-checkpoints" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tomg-group-umd/zero-model-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tomg-group-umd/zero-model-checkpoints with Docker Model Runner:
```
docker model run hf.co/tomg-group-umd/zero-model-checkpoints
```

Improve model card: Update license, add abstract, usage, and citation

by nielsr HF Staff - opened Aug 5, 2025

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+60

-2

nielsr

Aug 5, 2025

This PR significantly improves the model card by:

Updating the license metadata from cc to the more specific cc-by-nc-4.0, aligning with the license stated in the project's GitHub repository.
Adding the paper abstract, providing crucial context and an overview of the model's contribution and methodology.
Including a Python code snippet for sample usage, demonstrating how to load and use the model with the transformers library for quick inference.
Adding the BibTeX citation for the paper, enabling proper attribution in research.
Removing the empty "File information" section for a cleaner model card.

These updates enhance the discoverability, usability, and completeness of the model card for the Hugging Face community.

Improve model card: Update license, add abstract, usage, and citationde8b6320

kaiyuyue changed pull request status to merged Aug 5, 2025

kaiyuyue

Tom Goldstein's Lab at University of Maryland, College Park org Aug 5, 2025

I really appreciate this contribution, Niels!!!
Thank you very much!

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