SpiritSight
Collection
SpiritSight Agent: Advanced GUI Agent with One Look β’ 4 items β’ Updated
How to use SenseLLM/SpiritSight-Agent-2B with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("image-text-to-text", model="SenseLLM/SpiritSight-Agent-2B") # Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("SenseLLM/SpiritSight-Agent-2B", dtype="auto")How to use SenseLLM/SpiritSight-Agent-2B with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SenseLLM/SpiritSight-Agent-2B"
# 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-2B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/SenseLLM/SpiritSight-Agent-2B
How to use SenseLLM/SpiritSight-Agent-2B with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "SenseLLM/SpiritSight-Agent-2B" \
--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-2B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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-2B" \
--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-2B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use SenseLLM/SpiritSight-Agent-2B with Docker Model Runner:
docker model run hf.co/SenseLLM/SpiritSight-Agent-2B
π Paper β’ π€ Models β’ π Project Page β’ π Datasets
SpiritSight-Agent is a vision-based, end-to-end GUI agent that excels in GUI navigation tasks across various GUI platforms.
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 |
Coming soon.
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-2B.py
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},
}
We thank the following amazing projects that truly inspired us:
Base model
OpenGVLab/InternVL2-2B