Instructions to use AskUI/PTA-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AskUI/PTA-1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="AskUI/PTA-1", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("AskUI/PTA-1", trust_remote_code=True) model = AutoModelForMultimodalLM.from_pretrained("AskUI/PTA-1", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AskUI/PTA-1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AskUI/PTA-1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AskUI/PTA-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AskUI/PTA-1
- SGLang
How to use AskUI/PTA-1 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 "AskUI/PTA-1" \ --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": "AskUI/PTA-1", "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 "AskUI/PTA-1" \ --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": "AskUI/PTA-1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AskUI/PTA-1 with Docker Model Runner:
docker model run hf.co/AskUI/PTA-1
Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,8 @@ PTA (Prompt-to-Automation) is a vision language model for computer & phone autom
|
|
| 16 |
With only 270M parameters it outperforms much larger models in GUI text and element localization.
|
| 17 |
This enables low-latency computer automation with local execution.
|
| 18 |
|
|
|
|
|
|
|
| 19 |
**Model Input:** Screenshot + description_of_target_element
|
| 20 |
|
| 21 |
**Model Output:** BoundingBox for Target Element
|
|
|
|
| 16 |
With only 270M parameters it outperforms much larger models in GUI text and element localization.
|
| 17 |
This enables low-latency computer automation with local execution.
|
| 18 |
|
| 19 |
+
▶️ Try the demo at: [AskUI/PTA-1](https://huggingface.co/spaces/AskUI/PTA-1)
|
| 20 |
+
|
| 21 |
**Model Input:** Screenshot + description_of_target_element
|
| 22 |
|
| 23 |
**Model Output:** BoundingBox for Target Element
|