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

Libraries

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

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

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

update_ocr_postprocess

#19

by haipingwu - opened Jul 18, 2024

base: refs/heads/main

←

from: refs/pr/19

Discussion Files changed

-3

Files changed (1) hide show

processing_florence2.py +3 -3

processing_florence2.py CHANGED Viewed

@@ -596,7 +596,7 @@ class Florence2PostProcesser(object):
                 {
                     'TASK_NAME': 'ocr',
                     'PATTERN':  r'(.+?)<loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)>',
-                    'AREA_THRESHOLD': 0.01
                 },
                 {
                     'TASK_NAME': 'phrase_grounding',
@@ -1025,7 +1025,7 @@ class Florence2PostProcesser(object):
                     text,
                     pattern=pattern,
                     image_size=image_size,
-                    area_threshold=self.parse_tasks_configs[task].get('AREA_THRESHOLD', 0.01),
                 )
                 parsed_dict['ocr'] = instances
             elif task == 'phrase_grounding':
@@ -1085,4 +1085,4 @@ class Florence2PostProcesser(object):
             else:
                 raise ValueError("task {} is not supported".format(task))
-        return parsed_dict

                 {
                     'TASK_NAME': 'ocr',
                     'PATTERN':  r'(.+?)<loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)><loc_(\d+)>',
+                    'AREA_THRESHOLD': 0.00
                 },
                 {
                     'TASK_NAME': 'phrase_grounding',
                     text,
                     pattern=pattern,
                     image_size=image_size,
+                    area_threshold=self.parse_tasks_configs[task].get('AREA_THRESHOLD', 0.0),
                 )
                 parsed_dict['ocr'] = instances
             elif task == 'phrase_grounding':
             else:
                 raise ValueError("task {} is not supported".format(task))
+        return parsed_dict