Instructions to use TD788432/Florence-3-FT-DocVQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TD788432/Florence-3-FT-DocVQA with Transformers:

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

pipe = pipeline("image-text-to-text", model="TD788432/Florence-3-FT-DocVQA", trust_remote_code=True)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("TD788432/Florence-3-FT-DocVQA", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("TD788432/Florence-3-FT-DocVQA", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TD788432/Florence-3-FT-DocVQA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TD788432/Florence-3-FT-DocVQA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TD788432/Florence-3-FT-DocVQA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TD788432/Florence-3-FT-DocVQA

SGLang

How to use TD788432/Florence-3-FT-DocVQA 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 "TD788432/Florence-3-FT-DocVQA" \
    --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": "TD788432/Florence-3-FT-DocVQA",
		"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 "TD788432/Florence-3-FT-DocVQA" \
        --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": "TD788432/Florence-3-FT-DocVQA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TD788432/Florence-3-FT-DocVQA with Docker Model Runner:
```
docker model run hf.co/TD788432/Florence-3-FT-DocVQA
```

Florence-3-FT-DocVQA / model.safetensors

TD788432

Upload Florence2ForConditionalGeneration

52d1105 verified almost 2 years ago

Download

History Blame

1.08 GB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 3e2a763cd7ecd7970e84127157ebc056919bf067bf947bab680bfe6ea652874f
Size of remote file:: 1.08 GB
SHA256:: 49ca5193c55654d0a45185742d7586ae482fabf98ae4760f9cf49d9dd33e8421

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.