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

Libraries

How to use microsoft/Florence-2-large-ft 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-ft", trust_remote_code=True)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

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

Adding signatures retrieval

#36

by Shumatsurontek - opened Apr 9, 2025

base: refs/heads/main

←

from: refs/pr/36

Discussion Files changed

-2

Files changed (1) hide show

processing_florence2.py +8 -2

processing_florence2.py CHANGED Viewed

@@ -106,7 +106,9 @@ class Florence2Processor(ProcessorMixin):
             '<REGION_TO_CATEGORY>': 'pure_text',
             '<REGION_TO_DESCRIPTION>': 'pure_text',
             '<REGION_TO_OCR>': 'pure_text',
-            '<REGION_PROPOSAL>': 'bboxes'
         }
         self.task_prompts_without_inputs = {
@@ -117,7 +119,8 @@ class Florence2Processor(ProcessorMixin):
             '<MORE_DETAILED_CAPTION>': 'Describe with a paragraph what is shown in the image.',
             '<OD>': 'Locate the objects with category name in the image.',
             '<DENSE_REGION_CAPTION>': 'Locate the objects in the image, with their descriptions.',
-            '<REGION_PROPOSAL>': 'Locate the region proposals in the image.'
         }
         self.task_prompts_with_input = {
@@ -619,6 +622,9 @@ class Florence2PostProcesser(object):
                 },
                 {
                     'TASK_NAME': 'description_with_bboxes_or_polygons',
                 }
             ]
         }

             '<REGION_TO_CATEGORY>': 'pure_text',
             '<REGION_TO_DESCRIPTION>': 'pure_text',
             '<REGION_TO_OCR>': 'pure_text',
+            '<REGION_PROPOSAL>': 'bboxes',
+            # **New Added Tasks**
+            '<OCR_SIGNATURES>': 'pure_text'
         }
         self.task_prompts_without_inputs = {
             '<MORE_DETAILED_CAPTION>': 'Describe with a paragraph what is shown in the image.',
             '<OD>': 'Locate the objects with category name in the image.',
             '<DENSE_REGION_CAPTION>': 'Locate the objects in the image, with their descriptions.',
+            '<REGION_PROPOSAL>': 'Locate the region proposals in the image.',
+            '<OCR_SIGNATURES>': 'Locate the signatures in the image and return the text of the signatures.'
         }
         self.task_prompts_with_input = {
                 },
                 {
                     'TASK_NAME': 'description_with_bboxes_or_polygons',
+                },
+                {
+                    'TASK_NAME': 'ocr_signatures',
                 }
             ]
         }