Instructions to use ByteDance/Sa2VA-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ByteDance/Sa2VA-8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="ByteDance/Sa2VA-8B", trust_remote_code=True)
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("ByteDance/Sa2VA-8B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ByteDance/Sa2VA-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ByteDance/Sa2VA-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": "ByteDance/Sa2VA-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/ByteDance/Sa2VA-8B

SGLang

How to use ByteDance/Sa2VA-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 "ByteDance/Sa2VA-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": "ByteDance/Sa2VA-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 "ByteDance/Sa2VA-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": "ByteDance/Sa2VA-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 ByteDance/Sa2VA-8B with Docker Model Runner:
```
docker model run hf.co/ByteDance/Sa2VA-8B
```

nielsr HF Staff commited on Apr 15, 2025

Commit

2f58d7f

verified ·

1 Parent(s): f9264a3

Add video-text-to-text pipeline tag

Browse files

This PR improves the model card by adding the `pipeline_tag` and linking to the paper. This ensures the model can be found at https://huggingface.co/models?pipeline_tag=video-text-to-text&sort=trending.

Files changed (1) hide show

README.md +11 -12

README.md CHANGED Viewed

@@ -1,25 +1,24 @@
 ---
-license: apache-2.0
-pipeline_tag: image-text-to-text
-library_name: transformers
 base_model:
-  - OpenGVLab/InternVL2.5-8B
-base_model_relation: merge
 language:
-  - multilingual
 tags:
-  - Sa2VA
-  - custom_code
 ---
 # Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
 [\[📂 GitHub\]](https://github.com/magic-research/Sa2VA)
-[\[📜 Sa2VA paper\]](https://arxiv.org/abs/2501.04001)
 [\[🚀 Quick Start\]](#quick-start)
 ## Introduction
 Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels. It achieves comparable performance to SOTA MLLMs Qwen2-VL and InternVL2.5 on question-answering benchmarks. Additionally, Sa2VA possesses the visual prompt understanding and dense object segmentation capabilities that SOTA MLLMs Qwen2-VL and InternVL2.5 lack. Sa2VA achieves SOTA performance on both image and video grounding and segmentation benchmarks.
@@ -156,4 +155,4 @@ If you find this project useful in your research, please consider citing:
   journal={arXiv preprint},
   year={2025}
 }
-```

 ---
 base_model:
+- OpenGVLab/InternVL2.5-8B
 language:
+- multilingual
+library_name: transformers
+license: apache-2.0
+pipeline_tag: video-text-to-text
 tags:
+- Sa2VA
+- custom_code
+base_model_relation: merge
 ---
 # Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
+This repository contains the models based on [Sa2VA paper](https://arxiv.org/abs/2501.04001).
 [\[📂 GitHub\]](https://github.com/magic-research/Sa2VA)
 [\[🚀 Quick Start\]](#quick-start)
 ## Introduction
 Sa2VA is an MLLM capable of question answering, visual prompt understanding, and dense object segmentation at both image and video levels. It achieves comparable performance to SOTA MLLMs Qwen2-VL and InternVL2.5 on question-answering benchmarks. Additionally, Sa2VA possesses the visual prompt understanding and dense object segmentation capabilities that SOTA MLLMs Qwen2-VL and InternVL2.5 lack. Sa2VA achieves SOTA performance on both image and video grounding and segmentation benchmarks.
   journal={arXiv preprint},
   year={2025}
 }
+```