Instructions to use agentsea/paligemma-3b-ft-widgetcap-waveui-448 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use agentsea/paligemma-3b-ft-widgetcap-waveui-448 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-widgetcap-waveui-448")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("agentsea/paligemma-3b-ft-widgetcap-waveui-448")
model = AutoModelForMultimodalLM.from_pretrained("agentsea/paligemma-3b-ft-widgetcap-waveui-448", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use agentsea/paligemma-3b-ft-widgetcap-waveui-448 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-widgetcap-waveui-448"
# 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-widgetcap-waveui-448",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/agentsea/paligemma-3b-ft-widgetcap-waveui-448

SGLang

How to use agentsea/paligemma-3b-ft-widgetcap-waveui-448 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-widgetcap-waveui-448" \
    --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-widgetcap-waveui-448",
		"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-widgetcap-waveui-448" \
        --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-widgetcap-waveui-448",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use agentsea/paligemma-3b-ft-widgetcap-waveui-448 with Docker Model Runner:
```
docker model run hf.co/agentsea/paligemma-3b-ft-widgetcap-waveui-448
```

paligemma-3b-ft-widgetcap-waveui-448 / README.md

nph4rd

Update README.md

1d30251 verified about 2 years ago

preview code

Raw History Blame Contribute Delete

2.22 kB

	---
	datasets:
	- agentsea/wave-ui
	language:
	- en
	library_name: transformers
	---

	# Paligemma WaveUI


	Transformers [PaliGemma 3B 448-res weights](https://huggingface.co/google/paligemma-3b-pt-448), fine-tuned on the [WaveUI](https://huggingface.co/datasets/agentsea/wave-ui) dataset for object-detection.

	## Model Details

	### Model Description

	This fine-tune was done atop of the [Paligemma 448 Widgetcap](https://huggingface.co/google/paligemma-3b-ft-widgetcap-448) model, using the [WaveUI](https://huggingface.co/datasets/agentsea/wave-ui) 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](https://www.agentsea.ai/).

	- Developed by: https://agentsea.ai/
	- Language(s) (NLP): en
	- Finetuned from model: https://huggingface.co/google/paligemma-3b-ft-widgetcap-448

	### Demo

	You can find a demo for this model [here](https://huggingface.co/spaces/agentsea/paligemma-waveui).

	## 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:

	```python
	from transformers import AutoProcessor, PaliGemmaForConditionalGeneration

	model = PaliGemmaForConditionalGeneration.from_pretrained("agentsea/paligemma-3b-ft-widgetcap-waveui-448").eval()
	processor = AutoProcessor.from_pretrained("agentsea/paligemma-3b-ft-widgetcap-waveui-448")
	```

	## Data

	We used the [WaveUI](https://huggingface.co/datasets/agentsea/wave-ui) 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