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

Libraries

How to use microsoft/Florence-2-large with Transformers:

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

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

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("microsoft/Florence-2-large", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("microsoft/Florence-2-large", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use microsoft/Florence-2-large with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/microsoft/Florence-2-large

SGLang

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

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

adding space between task prompt and text input makes better/proper result

by flrngel - opened Jun 20, 2024

Discussion

flrngel

Jun 20, 2024

I think the example code should be changed like this.

def run_example(task_prompt, text_input=None):
    if text_input is None:
        prompt = task_prompt
    else:
-        prompt = task_prompt + text_input
+        prompt = task_prompt + " " + text_input

test image: http://farm3.staticflickr.com/2386/2532343535_41a2d3a9a0_z.jpg (from coco)
task prompt: Region to Description
text input: man on the back (without space)

output:

{'<REGION_TO_DESCRIPTION>': 'A woman with a large backpack in an airport terminal.'}

text input: man on the back (with prepending a space)
output:

{'<REGION_TO_DESCRIPTION>': "person on the back of a large green backpack with straps and buckles. \n\nThe backpack appears to be made of a durable material and has multiple pockets and compartments for storage. The straps are adjustable and the buckles are silver. The backpack is resting on a blue and white checkered floor.\n\nThere is a person's leg visible on the right side of the image, but they are not clearly visible. The background is blurred, so it is difficult to make out any other details."}

flrngel

Jun 20, 2024

I've checked the https://huggingface.co/microsoft/Florence-2-large/blob/main/sample_inference.ipynb

flrngel changed discussion status to closed Jun 20, 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