Instructions to use SenseLLM/SpiritSight-Agent-26B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SenseLLM/SpiritSight-Agent-26B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="SenseLLM/SpiritSight-Agent-26B")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SenseLLM/SpiritSight-Agent-26B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use SenseLLM/SpiritSight-Agent-26B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SenseLLM/SpiritSight-Agent-26B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SenseLLM/SpiritSight-Agent-26B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SenseLLM/SpiritSight-Agent-26B
- SGLang
How to use SenseLLM/SpiritSight-Agent-26B 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 "SenseLLM/SpiritSight-Agent-26B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SenseLLM/SpiritSight-Agent-26B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "SenseLLM/SpiritSight-Agent-26B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SenseLLM/SpiritSight-Agent-26B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SenseLLM/SpiritSight-Agent-26B with Docker Model Runner:
docker model run hf.co/SenseLLM/SpiritSight-Agent-26B
metadata
base_model:
- InternVL/InternVL2-26B
license: apache-2.0
library_name: transformers
pipeline_tag: image-text-to-text
SpiritSight Agent: Advanced GUI Agent with One Look
π Paper β’ π€ Models β’ π Project Page β’ π Datasets
Introduction
SpiritSight-Agent is a vision-based, end-to-end GUI agent that excels in GUI navigation tasks across various GUI platforms.
Models
We recommend fine-tuning the base model on custom data.
| Model | Checkpoint | Size | License |
|---|---|---|---|
| SpiritSight-Agent-2B-base | π€ HF Link | 2B | InternVL |
| SpiritSight-Agent-8B-base | π€ HF Link | 8B | InternVL |
| SpiritSight-Agent-26B-base | π€ HF Link | 26B | InternVL |
Datasets
Coming soon.
Inference
conda create -n spiritsight-agent python=3.9
pip install -r requirements.txt
pip install flash-attn==2.3.6 --no-build-isolation
python infer_SSAgent-26B.py
Citation
If you find this repo useful for your research, please kindly cite our paper:
@misc{huang2025spiritsightagentadvancedgui,
title={SpiritSight Agent: Advanced GUI Agent with One Look},
author={Zhiyuan Huang and Ziming Cheng and Junting Pan and Zhaohui Hou and Mingjie Zhan},
year={2025},
eprint={2503.03196},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2503.03196},
}
Acknowledgments
We thank the following amazing projects that truly inspired us:

