Instructions to use psp-dada/LLaVA-v1.6-Vicuna-13B-SENTINEL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use psp-dada/LLaVA-v1.6-Vicuna-13B-SENTINEL with Transformers:

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

pipe = pipeline("image-text-to-text", model="psp-dada/LLaVA-v1.6-Vicuna-13B-SENTINEL")
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 AutoModel
model = AutoModel.from_pretrained("psp-dada/LLaVA-v1.6-Vicuna-13B-SENTINEL", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use psp-dada/LLaVA-v1.6-Vicuna-13B-SENTINEL with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "psp-dada/LLaVA-v1.6-Vicuna-13B-SENTINEL"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "psp-dada/LLaVA-v1.6-Vicuna-13B-SENTINEL",
		"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/psp-dada/LLaVA-v1.6-Vicuna-13B-SENTINEL

SGLang

How to use psp-dada/LLaVA-v1.6-Vicuna-13B-SENTINEL 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 "psp-dada/LLaVA-v1.6-Vicuna-13B-SENTINEL" \
    --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": "psp-dada/LLaVA-v1.6-Vicuna-13B-SENTINEL",
		"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 "psp-dada/LLaVA-v1.6-Vicuna-13B-SENTINEL" \
        --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": "psp-dada/LLaVA-v1.6-Vicuna-13B-SENTINEL",
		"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 psp-dada/LLaVA-v1.6-Vicuna-13B-SENTINEL with Docker Model Runner:
```
docker model run hf.co/psp-dada/LLaVA-v1.6-Vicuna-13B-SENTINEL
```

psp-dada commited on Feb 7

Commit

103b6c3

verified ·

1 Parent(s): d88f276

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -6

README.md CHANGED Viewed

@@ -10,15 +10,18 @@ pipeline_tag: image-text-to-text
 library_name: transformers
 tags:
 - lora
 - llava
 ---
-# Model Card for ``psp-dada/LLaVA-v1.6-Vicuna-13B-SENTINEL`` | ICCV2025 | SENTINEL:<br>Mitigating Object Hallucinations via Sentence-Level Early Intervention <!-- omit in toc -->
 <a href='https://arxiv.org/abs/2507.12455'>
 <img src='https://img.shields.io/badge/Paper-Arxiv-purple'></a>
 <a href='https://github.com/pspdada/SENTINEL'>
-<img src='https://img.shields.io/badge/Github-Repo-Green'></a>
 <a href='https://huggingface.co/papers/2507.12455'>
 <img src='https://img.shields.io/badge/Discussion-HF-blue'></a>
 <a href='https://github.com/pspdada/SENTINEL/blob/main/LICENSE'>
@@ -26,7 +29,8 @@ tags:
 ## 🎊 News <!-- omit in toc -->
-- [2025.07.21] All code, data, and models are released!
 - [2025.06.26] 🎉 Our SENTINEL is accepted by **ICCV 2025**!
 ## 🚀 Overview <!-- omit in toc -->
@@ -88,10 +92,11 @@ This model is a PEFT (LoRA) adapter. You first need to load the base model (`lla
 If you find our model/code/data/paper helpful, please consider citing our papers 📝 and starring us ⭐️！
 ```bibtex
-@article{peng2025mitigating,
-  title={Mitigating Object Hallucinations via Sentence-Level Early Intervention},
   author={Peng, Shangpin and Yang, Senqiao and Jiang, Li and Tian, Zhuotao},
-  journal={arXiv preprint arXiv:2507.12455},
   year={2025}
 }
 ```

 library_name: transformers
 tags:
 - lora
+- bf16
 - llava
 ---
+# Model Card for ``psp-dada/LLaVA-v1.6-Vicuna-13B-SENTINEL`` | ICCV 2025 | SENTINEL:<br>Mitigating Object Hallucinations via Sentence-Level Early Intervention <!-- omit in toc -->
 <a href='https://arxiv.org/abs/2507.12455'>
 <img src='https://img.shields.io/badge/Paper-Arxiv-purple'></a>
+<a href='https://huggingface.co/datasets/psp-dada/SENTINEL'>
+<img src='https://img.shields.io/badge/Datasets-HF-Green'></a>
 <a href='https://github.com/pspdada/SENTINEL'>
+<img src='https://img.shields.io/badge/Github-Repo-orange'></a>
 <a href='https://huggingface.co/papers/2507.12455'>
 <img src='https://img.shields.io/badge/Discussion-HF-blue'></a>
 <a href='https://github.com/pspdada/SENTINEL/blob/main/LICENSE'>
 ## 🎊 News <!-- omit in toc -->
+- [2025.07.30] 🔍 Our work has been featured and explained by 52CV, check it out [here](https://mp.weixin.qq.com/s/Sfr1wdUCkeOLmj7NVWNUnw).
+- [2025.07.21] 📖 All code, data, and models are released!
 - [2025.06.26] 🎉 Our SENTINEL is accepted by **ICCV 2025**!
 ## 🚀 Overview <!-- omit in toc -->
 If you find our model/code/data/paper helpful, please consider citing our papers 📝 and starring us ⭐️！
 ```bibtex
+@inproceedings{peng2025mitigating,
+  title={Mitigating object hallucinations via sentence-level early intervention},
   author={Peng, Shangpin and Yang, Senqiao and Jiang, Li and Tian, Zhuotao},
+  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
+  pages={635--646},
   year={2025}
 }
 ```