Instructions to use bollscoasts/pix2act-weblinx-base-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bollscoasts/pix2act-weblinx-base-onnx with Transformers:

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

pipe = pipeline("image-text-to-text", model="bollscoasts/pix2act-weblinx-base-onnx")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("bollscoasts/pix2act-weblinx-base-onnx")
model = AutoModelForImageTextToText.from_pretrained("bollscoasts/pix2act-weblinx-base-onnx")

Transformers.js

How to use bollscoasts/pix2act-weblinx-base-onnx with Transformers.js:

// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';

// Allocate pipeline
const pipe = await pipeline('image-text-to-text', 'bollscoasts/pix2act-weblinx-base-onnx');

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use bollscoasts/pix2act-weblinx-base-onnx with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bollscoasts/pix2act-weblinx-base-onnx"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bollscoasts/pix2act-weblinx-base-onnx",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bollscoasts/pix2act-weblinx-base-onnx

SGLang

How to use bollscoasts/pix2act-weblinx-base-onnx 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 "bollscoasts/pix2act-weblinx-base-onnx" \
    --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": "bollscoasts/pix2act-weblinx-base-onnx",
		"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 "bollscoasts/pix2act-weblinx-base-onnx" \
        --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": "bollscoasts/pix2act-weblinx-base-onnx",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bollscoasts/pix2act-weblinx-base-onnx with Docker Model Runner:
```
docker model run hf.co/bollscoasts/pix2act-weblinx-base-onnx
```

Pix2Act-WebLINX-Base ONNX

ONNX export of McGill-NLP/pix2act-base-weblinx optimized for browser and server-side inference.

Model Details

Property	Value
Original Model	McGill-NLP/pix2act-base-weblinx
Architecture	Pix2Struct (Vision2Seq)
Parameters	~282M
Export Format	ONNX (opset 17)
Quantization	INT8 dynamic
Model Size	~1.17 GB (quantized)
Browser Eligible	Borderline (works with WebGPU)

Description

Pix2Act-WebLINX is fine-tuned on the WebLINX dataset for real-world web navigation tasks. It uses a pixel-only approach (no HTML/DOM access) making it ideal for:

Web automation tasks
GUI interaction from screenshots
Cross-platform browser control
Accessibility applications

Files

File	Size	Description
`encoder_model.onnx`	88 MB	Vision encoder
`decoder_model.onnx`	183 MB	Text decoder
`decoder_with_past.onnx`	170 MB	Decoder with KV-cache
`decoder_model_merged.onnx`	728 MB	Merged decoder (for Transformers.js)

Usage

With ONNX Runtime (Python)

import onnxruntime as ort
from transformers import AutoProcessor
from PIL import Image

# Load processor
processor = AutoProcessor.from_pretrained("bollscoasts/pix2act-weblinx-base-onnx")

# Load ONNX model
session = ort.InferenceSession("encoder_model.onnx")

# Process image
image = Image.open("screenshot.png")
inputs = processor(images=image, return_tensors="np")

# Run inference
outputs = session.run(None, dict(inputs))

With Transformers.js (Browser)

import { pipeline } from "@xenova/transformers";

// Load the ONNX model
const pipe = await pipeline("image-to-text", "bollscoasts/pix2act-weblinx-base-onnx");

// Run inference on screenshot
const result = await pipe(image);
console.log(result);

Export Details

Exported using HotelBench ONNX export utilities.

The original model was missing the image processor config, which was restored from google/pix2struct-base to enable ONNX export.

Performance

Browser (WebGPU): ~500-1000ms inference time
Server (CUDA): ~100-200ms inference time
Server (CPU): ~1-2s inference time

Citation

@article{pix2act,
  title={From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces},
  author={Shaw, Peter and Joshi, Mandar and Cohan, Iz and Berant, Jonathan and Pasupat, Panupong and Shin, Hexiang and Gur, Izzeddin and Kwiatkowski, Tom and Zhang, Kenton Lee},
  journal={NeurIPS 2023},
  year={2023}
}

@article{weblinx,
  title={WebLINX: Real-World Website Navigation with Multi-Turn Dialogue},
  author={Lù, Xing Han and Kasner, Zdeněk and Reddy, Siva},
  journal={ICML 2024},
  year={2024}
}

License

Apache 2.0 - See original model for full license details.

Downloads last month: 2

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for bollscoasts/pix2act-weblinx-base-onnx

Base model

McGill-NLP/pix2act-base-weblinx

Quantized

(1)

this model

bollscoasts
/

pix2act-weblinx-base-onnx