Instructions to use HuggingFaceM4/Florence-2-DocVQA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceM4/Florence-2-DocVQA with Transformers:

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

pipe = pipeline("image-text-to-text", model="HuggingFaceM4/Florence-2-DocVQA", trust_remote_code=True)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("HuggingFaceM4/Florence-2-DocVQA", trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained("HuggingFaceM4/Florence-2-DocVQA", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HuggingFaceM4/Florence-2-DocVQA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceM4/Florence-2-DocVQA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceM4/Florence-2-DocVQA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceM4/Florence-2-DocVQA

SGLang

How to use HuggingFaceM4/Florence-2-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 "HuggingFaceM4/Florence-2-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": "HuggingFaceM4/Florence-2-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 "HuggingFaceM4/Florence-2-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": "HuggingFaceM4/Florence-2-DocVQA",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceM4/Florence-2-DocVQA with Docker Model Runner:
```
docker model run hf.co/HuggingFaceM4/Florence-2-DocVQA
```

Error loading fine tuned model

by codegood - opened Jul 5, 2024

Discussion

codegood

Jul 5, 2024

I fine-tuned the Microsoft/Florence-2-base on my task. I can't load my model again due to the following error: AssertionError: only DaViT is supported for now. I see that you could pass through this error using a custom loading script.

Please guide me on how I can do the same. Thanks

codegood changed discussion title from Issue when fine tuning to Error loading fine tuned model Jul 5, 2024

andito

HuggingFaceM4 org Jul 5, 2024

Edit the config.json file. One of the model_type keys will have an empty value (""). Replace that with "davit"

andito changed discussion status to closed Jul 5, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment