Instructions to use gaostar/DeViL-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gaostar/DeViL-7B with Transformers:

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

pipe = pipeline("text-generation", model="gaostar/DeViL-7B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("gaostar/DeViL-7B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use gaostar/DeViL-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gaostar/DeViL-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gaostar/DeViL-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/gaostar/DeViL-7B

SGLang

How to use gaostar/DeViL-7B 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 "gaostar/DeViL-7B" \
    --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": "gaostar/DeViL-7B",
		"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 "gaostar/DeViL-7B" \
        --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": "gaostar/DeViL-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use gaostar/DeViL-7B with Docker Model Runner:
```
docker model run hf.co/gaostar/DeViL-7B
```

DeViL-7B / README.md

gaostar

Update README.md

0a29fd8 verified 8 days ago

preview code

raw

history blame contribute delete

1.76 kB

	---
	license: apache-2.0
	library_name: transformers
	base_model: DAMO-NLP-SG/VideoLLaMA3-7B
	tags:
	- multimodal
	- video-llm
	- video-understanding
	- video-grounding
	- spatio-temporal-grounding
	- temporal-grounding
	- referring-expression-comprehension
	- grounding
	- reasoning
	- custom_code
	- pytorch
	---

	<div align="center">

	# DeViL-7B

	Official checkpoint for "Detector-Empowered Video Large Language Model for Efficient Spatio-Temporal Grounding"

	[Paper](https://arxiv.org/abs/2512.06673) \| [Code](https://github.com/gaostar123/DeViL)

	</div>

	<p align="center">
	<img src="https://raw.githubusercontent.com/gaostar123/DeViL/main/assets/intro_v10.png" alt="DeViL teaser" width="100%">
	</p>

	## Overview

	DeViL is a detector-empowered video large language model designed for efficient spatio-temporal video grounding (STVG) and grounded video reasoning. Instead of relying on long autoregressive coordinate decoding or expensive candidate construction, DeViL offloads dense spatial grounding to a fully parallel detector. It distills the user query into a detector-compatible reference-semantic token and uses temporal consistency regularization to maintain object coherence across frames.

	This repository hosts the official DeViL-7B checkpoint released by the authors.

	## Highlights

	- Detector-empowered grounding for efficient spatio-temporal localization
	- Strong performance reported in the paper: 43.1 m_vIoU on HC-STVG and 14.33 FPS
	- Preserves the backbone MLLM's general video understanding and reasoning ability
	- Supports both image and video inputs in the official demo pipeline

	## Links

	- Paper: https://arxiv.org/abs/2512.06673
	- Code: https://github.com/gaostar123/DeViL