Instructions to use lumimate/PhoneUIAnchor-829M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lumimate/PhoneUIAnchor-829M with Transformers:

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

pipe = pipeline("image-text-to-text", model="lumimate/PhoneUIAnchor-829M", trust_remote_code=True)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("lumimate/PhoneUIAnchor-829M", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("lumimate/PhoneUIAnchor-829M", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lumimate/PhoneUIAnchor-829M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lumimate/PhoneUIAnchor-829M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lumimate/PhoneUIAnchor-829M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lumimate/PhoneUIAnchor-829M

SGLang

How to use lumimate/PhoneUIAnchor-829M 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 "lumimate/PhoneUIAnchor-829M" \
    --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": "lumimate/PhoneUIAnchor-829M",
		"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 "lumimate/PhoneUIAnchor-829M" \
        --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": "lumimate/PhoneUIAnchor-829M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lumimate/PhoneUIAnchor-829M with Docker Model Runner:
```
docker model run hf.co/lumimate/PhoneUIAnchor-829M
```

PhoneUIAnchor-829M / UPLOAD.md

lumimate

Rename model to PhoneUIAnchor-829M

aba4d5a verified 26 days ago

preview code

Raw

History Blame Contribute Delete

689 Bytes

	# Hugging Face 发布步骤

	本目录可以直接作为 Hugging Face 模型仓库上传。

	```bash
	pip install -U huggingface_hub
	hf auth login
	proxychains -q hf repos create PhoneUIAnchor-829M --repo-type model
	proxychains -q hf upload lumimate/PhoneUIAnchor-829M . --repo-type model \
	--exclude '.cache/' --exclude '__pycache__/'
	```

	上传后运行在线模型测试：

	```bash
	python inference_example.py \
	--model lumimate/PhoneUIAnchor-829M \
	--image /path/to/ui_screenshot.png \
	--prompt 'Where is the "Settings" element? (Output the center coordinates of the target)'
	```

	模型包含 Florence-2 自定义源码，调用方必须使用
	`trust_remote_code=True`。