Downloads · 30 days
12
9% of all-time downloads
johnnietien/JTPA2.5-VL-3B-phone-agent-vi
JTPA2.5-VL-3B-phone-agent-vi is a image-to-text model from johnnietien. Use it when you need a caption or text from an image. It is set up for transformers. The card lists the license as apache-2.0.
A lightweight Vietnamese-optimized vision-language model for Android phone automation. This model understands Vietnamese UI interactions and generates structured action sequences for mobile device control.
Downloads · 30 days
12
9% of all-time downloads
All-time downloads
132
Public
Parameters
3.8B
7.5 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors7.5 GB · 100%
From the Hugging Face model README
A lightweight Vietnamese-optimized vision-language model for Android phone automation. This model understands Vietnamese UI interactions and generates structured action sequences for mobile device control.
This model excels at:
Input: Screenshot + Vietnamese instruction Output: Structured action in JSON format { "action": "tap", "x": 540, "y": 1200, "reason": "Click on the search button" }
python -m vllm.entrypoints.openai.api_server --model johnnietien/JTPA2.5-VL-3B-phone-agent-vi --trust-remote-code --port 8000
import requests import base64
def encode_image(path): with open(path, "rb") as f: return base64.b64encode(f.read()).decode("utf-8")
payload = { "model": "JTPA2.5-VL-3B-phone-agent-vi", "messages": [{ "role": "user", "content": [ {"type": "input_text", "text": "Mở ứng dụng MoMo"}, {"type": "input_image", "image_url": {"url": f"data:image/jpeg;base64,{encode_image('screenshot.png')}"}} ] }], "max_tokens": 256 }
response = requests.post("http://localhost:8000/v1/chat/completions", json=payload) print(response.json()["choices"]["message"]["content"])
Perfect for:
| Aspect | Details |
|---|---|
| Model Size | 3B parameters |
| Context Length | 4K tokens |
| Inference Speed | ~0.5-1.0 sec/action (T4 GPU) |
| VRAM Requirement | 6-8 GB (BF16), 4-6 GB (quantized) |
| Supported Actions | tap, type, swipe, back, home, wait |
✅ Intended for:
❌ Not intended for:
@misc{jtpa2024phone, author = {Johnnie Tien}, title = {JTPA2.5-VL-3B-Phone-Agent-VI: Vietnamese Mobile GUI Agent}, year = {2024}, howpublished = {\url{https://huggingface.co/johnnietien/JTPA2.5-VL-3B-phone-agent-vi}} }
Version: 1.0 | Status: Production-Ready | Last Updated: December 2024
[More Information Needed]