Instructions to use maxiw/Florence-2-ScreenQA-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maxiw/Florence-2-ScreenQA-base with Transformers:

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

pipe = pipeline("image-text-to-text", model="maxiw/Florence-2-ScreenQA-base", trust_remote_code=True)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("maxiw/Florence-2-ScreenQA-base", trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained("maxiw/Florence-2-ScreenQA-base", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use maxiw/Florence-2-ScreenQA-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "maxiw/Florence-2-ScreenQA-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maxiw/Florence-2-ScreenQA-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/maxiw/Florence-2-ScreenQA-base

SGLang

How to use maxiw/Florence-2-ScreenQA-base 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 "maxiw/Florence-2-ScreenQA-base" \
    --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": "maxiw/Florence-2-ScreenQA-base",
		"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 "maxiw/Florence-2-ScreenQA-base" \
        --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": "maxiw/Florence-2-ScreenQA-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use maxiw/Florence-2-ScreenQA-base with Docker Model Runner:
```
docker model run hf.co/maxiw/Florence-2-ScreenQA-base
```

Florence-2-ScreenQA-base

This is fine-tuned version of microsoft/Florence-2-base on RICO-ScreenQA. It can be used to extract information from screenshots.

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: [More Information Needed]
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Model type: [More Information Needed]
Finetuned from model: microsoft/Florence-2-base

Model Sources [optional]

Repository: [More Information Needed]
Demo: HF Space

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Downloads last month: 31

Safetensors

Model size

0.3B params

Tensor type

F16

Inference Providers NEW

Image-Text-to-Text

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

Model tree for maxiw/Florence-2-ScreenQA-base

Base model

microsoft/Florence-2-base

Finetuned

(20)

this model

maxiw
/

Florence-2-ScreenQA-base

Florence-2-ScreenQA-base

Model Details

Model Description

Model Sources [optional]

How to Get Started with the Model

Training Details

Training Data

Training Procedure

Preprocessing [optional]

Training Hyperparameters

Speeds, Sizes, Times [optional]

Model tree for maxiw/Florence-2-ScreenQA-base

Dataset used to train maxiw/Florence-2-ScreenQA-base

Space using maxiw/Florence-2-ScreenQA-base 1