Instructions to use Falconsai/florence-2-invoice with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Falconsai/florence-2-invoice with Transformers:

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

pipe = pipeline("image-text-to-text", model="Falconsai/florence-2-invoice", trust_remote_code=True)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Falconsai/florence-2-invoice", trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained("Falconsai/florence-2-invoice", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Falconsai/florence-2-invoice with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Falconsai/florence-2-invoice

SGLang

How to use Falconsai/florence-2-invoice 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 "Falconsai/florence-2-invoice" \
    --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": "Falconsai/florence-2-invoice",
		"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 "Falconsai/florence-2-invoice" \
        --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": "Falconsai/florence-2-invoice",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Falconsai/florence-2-invoice with Docker Model Runner:
```
docker model run hf.co/Falconsai/florence-2-invoice
```

mstatt commited on Jul 14, 2024

Commit

6cf50c8

verified ·

1 Parent(s): 3d5660a

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -18

README.md CHANGED Viewed

@@ -16,24 +16,12 @@ tags: []
 `Falconsai/florence-2-invoice` is a fine-tuned version of the `microsoft/Florence-2-base-ft` model. This model has been specifically trained to identify and extract key fields from invoice images. The fine-tuning process utilized a curated dataset of invoices annotated to recognize the following fields:
-- Billing address
-- Discount percentage
-- Due date
-- Email client
-- Header
-- Invoice date
-- Invoice number
-- Name client
-- Products
-- Remise
-- Shipping address
-- Subtotal
-- Tax
-- Tax percentage
-- Tel client
-- Total
-## Model Details
 ### Base Model
 The base model used for fine-tuning is `microsoft/Florence-2-base-ft`, a state-of-the-art vision model developed by Microsoft.

 `Falconsai/florence-2-invoice` is a fine-tuned version of the `microsoft/Florence-2-base-ft` model. This model has been specifically trained to identify and extract key fields from invoice images. The fine-tuning process utilized a curated dataset of invoices annotated to recognize the following fields:
+- Billing address, - Discount percentage, - Due date
+- Email client, - Header, - Invoice date
+- Invoice number, - Name client, - Products
+- Remise, - Shipping address, - Subtotal
+- Tax, - Tax percentage, - Tel client, - Total
 ### Base Model
 The base model used for fine-tuning is `microsoft/Florence-2-base-ft`, a state-of-the-art vision model developed by Microsoft.