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

Libraries

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

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

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

ValueError: If no `decoder_input_ids` or `decoder_inputs_embeds` are passed, `input_ids` cannot be `None`

#75

by dutta18 - opened Oct 4, 2024

Discussion

dutta18

Oct 4, 2024

I am trying to get the decoder hidden state of the florence 2 model. I was following this https://huggingface.co/microsoft/Florence-2-large/blob/main/modeling_florence2.py to understand the parameters that goes into the forward method. I tried something like

Pass inputs to the model with output_hidden_states=True to get hidden states

with torch.no_grad():
outputs = model(
input_ids=inputs["input_ids"],
pixel_values=inputs["pixel_values"],
attention_mask=inputs["attention_mask"],
output_hidden_states=True, # Request hidden states
)

But doing this I'm getting this error:

ValueError: If no decoder_input_ids or decoder_inputs_embeds are passed, input_ids cannot be None. Please pass either input_ids or decoder_input_ids or decoder_inputs_embeds.

Also I am using this model for inference only, what does the decoder_input_ids mean and where I can find this to pass in the forward method.

Darkyy

Dec 25, 2024

I have the exact same issue. If you have found the solution to it then please let me know!

myn0908

Jan 13, 2025

@dutta18 If you using model(...) , you need to load labels tokenize like this:
outputs = self.model(
input_ids=input_ids,
pixel_values=pixel_values,
labels=labels
)
It'll work and for inference, you should use model.generate

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