Instructions to use aimagelab/ReflectiVA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aimagelab/ReflectiVA with Transformers:

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

pipe = pipeline("image-text-to-text", model="aimagelab/ReflectiVA")
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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("aimagelab/ReflectiVA", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use aimagelab/ReflectiVA with vLLM:

Install from pip and serve model

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

SGLang

How to use aimagelab/ReflectiVA 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 "aimagelab/ReflectiVA" \
    --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": "aimagelab/ReflectiVA",
		"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 "aimagelab/ReflectiVA" \
        --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": "aimagelab/ReflectiVA",
		"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 aimagelab/ReflectiVA with Docker Model Runner:
```
docker model run hf.co/aimagelab/ReflectiVA
```

fede97 commited on Apr 5, 2025

Commit

2ed2885

verified ·

1 Parent(s): 9d00372

update bibtex

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -27,11 +27,11 @@ For more information, visit our [ReflectiVA repository](https://github.com/aimag
 If you make use of our work, please cite our repo:
 ```bibtex
-@article{cocchi2024augmenting,
   title={{Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering}},
   author={Cocchi, Federico and Moratelli, Nicholas and Cornia, Marcella and Baraldi, Lorenzo and Cucchiara, Rita},
-  journal={arXiv},
-  year={2024}
 }
 ```

 If you make use of our work, please cite our repo:
 ```bibtex
+@inproceedings{cocchi2024augmenting,
   title={{Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering}},
   author={Cocchi, Federico and Moratelli, Nicholas and Cornia, Marcella and Baraldi, Lorenzo and Cucchiara, Rita},
+  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
+  year={2025}
 }
 ```