microsoft
/

Florence-2-base-ft

Image-Text-to-Text

Model card Files Files and versions

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

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

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
```

Resources

View closed (9)

Update README.md

#31 opened 8 months ago by

Added the `GenerationMixin`

#30 opened 11 months ago by

iamdanialkamali

data

#28 opened about 1 year ago by

data

#27 opened about 1 year ago by

data

#26 opened about 1 year ago by

data

#25 opened about 1 year ago by

Update modeling_florence2.py

#24 opened about 1 year ago by

Which one should I use, Florence-2-base-ft and Florence-2-base?

#23 opened over 1 year ago by

Fix invalid escape sequences

#22 opened over 1 year ago by

How to get decoder final hidden state?

#21 opened almost 2 years ago by

Add get_output_embeddings

#18 opened almost 2 years ago by

Take out caption restriction for personal use

#17 opened almost 2 years ago by

gpu usage

#16 opened almost 2 years ago by

unable to load the model, flash-attn problem

#15 opened almost 2 years ago by

Unable to load fine tuned model from local directory

#14 opened almost 2 years ago by

Finetuning Token Length Limit

#12 opened almost 2 years ago by

Swift now supports inference, training, and deployment of the Florence models.

#11 opened almost 2 years ago by

Efficient inference

#10 opened almost 2 years ago by

cuongnguyenxuan

Running in CPU

#9 opened almost 2 years ago by

Running Florence on M1 Mac

#8 opened almost 2 years ago by

Amazing model and very promissing

#5 opened almost 2 years ago by

paulorodriguesjr

Trust remote code requirement - why?

#4 opened almost 2 years ago by