Instructions to use SenseLLM/SpiritSight-Agent-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SenseLLM/SpiritSight-Agent-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="SenseLLM/SpiritSight-Agent-8B")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("SenseLLM/SpiritSight-Agent-8B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use SenseLLM/SpiritSight-Agent-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SenseLLM/SpiritSight-Agent-8B" # 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-8B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/SenseLLM/SpiritSight-Agent-8B
- SGLang
How to use SenseLLM/SpiritSight-Agent-8B 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-8B" \ --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-8B", "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-8B" \ --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-8B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use SenseLLM/SpiritSight-Agent-8B with Docker Model Runner:
docker model run hf.co/SenseLLM/SpiritSight-Agent-8B
A general question about the paper
Hi,
Can I ask when you mentioned " To avoid ambiguity, we provide addi- tional contextual information for elements that appear multi- ple times in the screenshots.", is it possible to give some examples? I am so curious about this part.
Thank you
Thank you for your interest in our work. The "additional contextual information" refers to the "sibling" elements of that element, that is, elements that share the same parent element as it. These sibling elements are usually visually close to that element, thus helping to determine the element object.