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

Libraries

How to use ucsahin/Florence-2-large-TableDetection with Transformers:

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

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

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ucsahin/Florence-2-large-TableDetection with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ucsahin/Florence-2-large-TableDetection

SGLang

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

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

TypeError need help

by ss22s - opened Jun 26, 2024

Discussion

ss22s

Jun 26, 2024

•

edited Jun 26, 2024

when i was fine-tuning the Florence-2-base-FT, i meet one problem, shows that:

Traceback (most recent call last):
File "/home/Florence-2/fine_turning.py", line 175, in
trainer.train()
File "/opt/conda/lib/python3.10/site-packages/transformers/trainer.py", line 1885, in train
return inner_training_loop(
File "/opt/conda/lib/python3.10/site-packages/transformers/trainer.py", line 2216, in _inner_training_loop
tr_loss_step = self.training_step(model, inputs)
File "/opt/conda/lib/python3.10/site-packages/transformers/trainer.py", line 3238, in training_step
loss = self.compute_loss(model, inputs)
File "/opt/conda/lib/python3.10/site-packages/transformers/trainer.py", line 3264, in compute_loss
outputs = model(**inputs)
File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/root/.cache/huggingface/modules/transformers_modules/modeling_florence2.py", line 2760, in forward
return Florence2Seq2SeqLMOutput(
TypeError: Florence2Seq2SeqLMOutput.init() got an unexpected keyword argument 'loss'

can you help me, thx

ucsahin

Owner Jun 26, 2024

•

edited Jun 26, 2024

Did you try to load the model with the PR fix mentioned in https://huggingface.co/blog/finetune-florence2?

Like this:
model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-base-ft", trust_remote_code=True, revision='refs/pr/6').to(device)
processor = AutoProcessor.from_pretrained("microsoft/Florence-2-base-ft", trust_remote_code=True, revision='refs/pr/6')

ss22s

Jun 27, 2024

The problem has been solved, thanks for your suggestion~
This issue appears to be a code bug that has been fixed by the author: https://huggingface.co/microsoft/Florence-2-large/discussions/12#66752ee0ec54ee155826d156

ss22s changed discussion status to closed Jun 27, 2024

DHANNUSSH

Oct 21, 2025

i am running the same code as in notebook but not working with some attribute error

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