Instructions to use ByteDance/Sa2VA-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ByteDance/Sa2VA-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="ByteDance/Sa2VA-4B", 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-4B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ByteDance/Sa2VA-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ByteDance/Sa2VA-4B"
# 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-4B",
		"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-4B

SGLang

How to use ByteDance/Sa2VA-4B 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-4B" \
    --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-4B",
		"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-4B" \
        --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-4B",
		"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-4B with Docker Model Runner:
```
docker model run hf.co/ByteDance/Sa2VA-4B
```

bitersun commited on Sep 7, 2025

Commit

0604e3c

1 Parent(s): b5ffed2

fix

Browse files

Files changed (1) hide show

modeling_sa2va_chat.py +2 -2

modeling_sa2va_chat.py CHANGED Viewed

@@ -545,7 +545,7 @@ class Sa2VAChatModel(PreTrainedModel):
         self.gen_config = GenerationConfig(**default_generation_kwargs)
         self.init_prediction_config = True
         self.torch_dtype = torch_dtype
-        self.to(torch_dtype)
         self.extra_image_processor = DirectResize(target_length=1024, )
         # for multi image process
         self.min_dynamic_patch = 1
@@ -623,7 +623,7 @@ class Sa2VAChatModel(PreTrainedModel):
                 extra_pixel_values = []
                 ori_image_size = video[0].size
                 for frame_idx, frame_image in enumerate(video):
-                    assert ori_image_size == frame_image.size
                     g_image = np.array(frame_image)  # for grounding
                     g_image = self.extra_image_processor.apply_image(g_image)
                     g_image = torch.from_numpy(g_image).permute(2, 0, 1).contiguous()

         self.gen_config = GenerationConfig(**default_generation_kwargs)
         self.init_prediction_config = True
         self.torch_dtype = torch_dtype
+        # self.to(torch_dtype)
         self.extra_image_processor = DirectResize(target_length=1024, )
         # for multi image process
         self.min_dynamic_patch = 1
                 extra_pixel_values = []
                 ori_image_size = video[0].size
                 for frame_idx, frame_image in enumerate(video):
+                    # assert ori_image_size == frame_image.size
                     g_image = np.array(frame_image)  # for grounding
                     g_image = self.extra_image_processor.apply_image(g_image)
                     g_image = torch.from_numpy(g_image).permute(2, 0, 1).contiguous()