Instructions to use aipib/Florence-2-FT-JP-OCR2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aipib/Florence-2-FT-JP-OCR2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="aipib/Florence-2-FT-JP-OCR2", trust_remote_code=True)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("aipib/Florence-2-FT-JP-OCR2", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("aipib/Florence-2-FT-JP-OCR2", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aipib/Florence-2-FT-JP-OCR2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aipib/Florence-2-FT-JP-OCR2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aipib/Florence-2-FT-JP-OCR2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/aipib/Florence-2-FT-JP-OCR2

SGLang

How to use aipib/Florence-2-FT-JP-OCR2 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 "aipib/Florence-2-FT-JP-OCR2" \
    --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": "aipib/Florence-2-FT-JP-OCR2",
		"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 "aipib/Florence-2-FT-JP-OCR2" \
        --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": "aipib/Florence-2-FT-JP-OCR2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use aipib/Florence-2-FT-JP-OCR2 with Docker Model Runner:
```
docker model run hf.co/aipib/Florence-2-FT-JP-OCR2
```

Florence-2-FT-JP-OCR2

This model is a fine-tuned version of microsoft/Florence-2-base-ft on EtashGuha/JapaneseDocQA dataset. It achieves the following results on the evaluation set:

Loss: 2.7551

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-06
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss
14.8441	0.5563	100	3.2737
14.1581	1.1168	200	3.1344
13.4486	1.6732	300	3.0362
13.287	2.2337	400	2.9634
12.9018	2.7900	500	2.9081
12.6016	3.3505	600	2.8683
12.5607	3.9068	700	2.8310
12.4259	4.4673	800	2.8060
12.2114	5.0278	900	2.7858
12.1777	5.5841	1000	2.7680
12.01	6.1446	1100	2.7604
12.0395	6.7010	1200	2.7551

Framework versions

Transformers 4.48.0.dev0
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.0

Downloads last month: 5

Safetensors

Model size

0.3B params

Tensor type

F32

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for aipib/Florence-2-FT-JP-OCR2

Base model

microsoft/Florence-2-base-ft

Finetuned

(23)

this model

aipib
/

Florence-2-FT-JP-OCR2

Florence-2-FT-JP-OCR2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for aipib/Florence-2-FT-JP-OCR2

Dataset used to train aipib/Florence-2-FT-JP-OCR2