Instructions to use EurekaTian/SyncPro-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EurekaTian/SyncPro-SFT with Transformers:

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

pipe = pipeline("image-text-to-text", model="EurekaTian/SyncPro-SFT")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("EurekaTian/SyncPro-SFT")
model = AutoModelForMultimodalLM.from_pretrained("EurekaTian/SyncPro-SFT", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EurekaTian/SyncPro-SFT with vLLM:

Install from pip and serve model

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

SGLang

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

SyncPro-SFT

SyncPro-SFT is the official supervised checkpoint for SyncPro: Synchronous Reasoning and Responding for Proactive Streaming Video Understanding.

SyncPro model architecture and streaming attention map

SyncPro synchronously decodes an internal reasoning stream and an external response stream under a causal streaming attention map.

Model

SyncPro forks the decoder into synchronous internal-reasoning and external-response branches. At each streaming step, it learns whether to remain silent, reason internally, or speak, while preserving causal processing.

This checkpoint was initialized from Qwen/Qwen3.5-4B and trained on 189,403 streaming trajectories using:

split action loss over the dual-stream grammar;
Action Temporal Ranking (ATR) against nearby hard negatives;
dual LoRA with rank 64, alpha 128, and dropout 0.05;
fixed additive branch merging with gamma = 0.5.

The release contains merged BF16 inference weights. Optimizer shards, scheduler state, RNG state, and other resume-only training artifacts are intentionally excluded. Inference code and benchmark adapters are documented in the SyncPro repository.

Data and intended use

The model is intended for research on causal streaming-video understanding, proactive response timing, and separated internal/external generation. Training annotations are available in SyncPro-189k. Source videos are not redistributed and must be obtained from their original publishers under the applicable terms.

The checkpoint may inherit limitations and biases from Qwen3.5-4B and the public research datasets used for training. It should not be treated as a safety-critical monitoring system.

License

The model weights are released under the Apache License 2.0. The annotation dataset has separate licensing and source-specific terms described on its dataset card.

Citation

@misc{tian2026syncpro,
  title  = {SyncPro: Synchronous Reasoning and Responding for
            Proactive Streaming Video Understanding},
  author = {Tian, Xueyun and Xu, Bingbing and Liu, Jiaming and
            Yu, Jinpeng and Shi, Yang and Zhao, Yu and
            Huang, Ruihua and Wang, Yuanzhuo and Shen, Huawei},
  year   = {2026},
  url    = {https://eureka-maggie.github.io/SyncPro/}
}

Downloads last month: -

Safetensors

Model size

5B params

Tensor type

BF16

Model tree for EurekaTian/SyncPro-SFT

Base model

Qwen/Qwen3.5-4B-Base

Finetuned

Qwen/Qwen3.5-4B

Finetuned

(976)

this model

Finetunes

1 model

EurekaTian
/

SyncPro-SFT