Instructions to use LEONW24/BEPA-7B-S2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LEONW24/BEPA-7B-S2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="LEONW24/BEPA-7B-S2")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("LEONW24/BEPA-7B-S2")
model = AutoModelForMultimodalLM.from_pretrained("LEONW24/BEPA-7B-S2", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LEONW24/BEPA-7B-S2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LEONW24/BEPA-7B-S2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LEONW24/BEPA-7B-S2",
		"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/LEONW24/BEPA-7B-S2

SGLang

How to use LEONW24/BEPA-7B-S2 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 "LEONW24/BEPA-7B-S2" \
    --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": "LEONW24/BEPA-7B-S2",
		"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 "LEONW24/BEPA-7B-S2" \
        --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": "LEONW24/BEPA-7B-S2",
		"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 LEONW24/BEPA-7B-S2 with Docker Model Runner:
```
docker model run hf.co/LEONW24/BEPA-7B-S2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

BEPA-7B-S2

From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation

🌐 Project Page | 📑 arXiv Paper | 💻 GitHub

🏆 #1 Open-Source End-to-End Model on OSWorld (15 steps): Achieves 32.13% success rate
📊 Extreme Data Efficiency: Matches GUI-OWL-7B performance using only 128 training tasks

Model Description

BEPA-7B-S2 is a GUI agent model fine-tuned from UI-TARS-1.5-7B using the BEPA (Bi-Level Expert-to-Policy Assimilation) framework. This model achieves state-of-the-art performance among open-source end-to-end models on the OSWorld benchmark.

Key Results

Method	D_{expert_only}	D_train	D_{held_out}	Overall (%)
UITARS1.5-7B	18.52	55.12	5.74	22.87
GRPO	11.11	58.02	5.32	23.60
BEPA (ours)	35.19	73.23	10.30	32.13

BEPA improves UI-TARS-1.5-7B from 22.87% to 32.13% on OSWorld-Verified (+9.26 points, +40.5% relative improvement).

BEPA Framework

BEPA Overview

BEPA addresses two key challenges when using expert trajectories for training end-to-end GUI policies:

Structural Mismatch: Framework traces interleave multiple roles (planning, execution, grounding) that end-to-end policies cannot directly imitate.
Distribution Gap: Even after format conversion, trajectories remain far from the base-policy manifold.

LEVEL-1: Self-Rolled Execution

Transforms alien expert traces into policy-compatible trajectories by abstracting expert trajectories into compact natural-language plans, then letting the base policy act in the environment with plan conditioning.

LEVEL-2: Self-Aligned Assimilation

Dynamically maintains a per-task cache, injecting guided trajectories into GRPO updates only upon total on-policy failure. The cache is continuously refreshed with the policy's own successful executions.

Citation

@misc{wang2026offpolicyonpolicyenhancinggui,
      title={From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation},
      author={Zezhou Wang and Ziyun Zhang and Xiaoyi Zhang and Zhuzhong Qian and Yan Lu},
      year={2026},
      eprint={2601.05787},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2601.05787},
}