Instructions to use agentsea/paligemma-3b-ft-waveui-896 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use agentsea/paligemma-3b-ft-waveui-896 with Transformers:

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

pipe = pipeline("image-text-to-text", model="agentsea/paligemma-3b-ft-waveui-896")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("agentsea/paligemma-3b-ft-waveui-896")
model = AutoModelForImageTextToText.from_pretrained("agentsea/paligemma-3b-ft-waveui-896")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use agentsea/paligemma-3b-ft-waveui-896 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "agentsea/paligemma-3b-ft-waveui-896"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "agentsea/paligemma-3b-ft-waveui-896",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/agentsea/paligemma-3b-ft-waveui-896

SGLang

How to use agentsea/paligemma-3b-ft-waveui-896 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 "agentsea/paligemma-3b-ft-waveui-896" \
    --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": "agentsea/paligemma-3b-ft-waveui-896",
		"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 "agentsea/paligemma-3b-ft-waveui-896" \
        --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": "agentsea/paligemma-3b-ft-waveui-896",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use agentsea/paligemma-3b-ft-waveui-896 with Docker Model Runner:
```
docker model run hf.co/agentsea/paligemma-3b-ft-waveui-896
```

Paligemma WaveUI

Transformers PaliGemma 3B 896-res weights, fine-tuned on the WaveUI dataset for object-detection.

Model Details

Model Description

This fine-tune was done atop of the Paligemma 896 model, using the WaveUI dataset, which contains ~80k examples of labeled UI elements.

The fine-tune was done for the object detection task. Specifically, this model aims to perform well at UI element detection, as part of a wider effort to enable our open-source toolkit for building agents at AgentSea.

Developed by: https://agentsea.ai/
Language(s) (NLP): en
Finetuned from model: https://huggingface.co/google/paligemma-3b-pt-896

Demo

You can find a demo for this model here.

Notes

The only task used in the fine-tune was the object detection task, so it might not perform well in other types of tasks.

Usage

To start using this model, run the following:

from transformers import AutoProcessor, PaliGemmaForConditionalGeneration

model = PaliGemmaForConditionalGeneration.from_pretrained("agentsea/paligemma-3b-ft-waveui-896").eval()
processor = AutoProcessor.from_pretrained("agentsea/paligemma-3b-ft-waveui-896")

Data

We used the WaveUI dataset for this fine-tune. Before using it, we preprocessed the data to use the Paligemma bounding-box format.

Evaluation

We calculated the mean IoU over 1024 examples of the test set using 3 different closed-source models: Gemini 1.5 Pro, Claude 3.5 Sonnet and GPT 4o. We also ran this same calculation using the PaliGemma WaveUI fine-tunes. We obtained the following values:

Gemini 1.5 Pro: 0.12
Claude 3.5 Sonnet: 0.05
GPT 4o: 0.05
PaliGemma Widgetcap+WaveUI 448: 0.40
PaliGemma WaveUI 896: 0.49

Downloads last month: 4

Safetensors

Model size

3B params

Tensor type

F32

Inference Providers NEW

Image-Text-to-Text

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

Dataset used to train agentsea/paligemma-3b-ft-waveui-896

Space using agentsea/paligemma-3b-ft-waveui-896 1

Collection including agentsea/paligemma-3b-ft-waveui-896

WaveUI

Collection

WaveUI is a collection of datasets and tools to improve UI object detection • 5 items • Updated Mar 2 • 10