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, AutoModelForMultimodalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

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
```

unexpected keyword argument 'loss' - Fine tuning for CAPTIONS

#27

by ksooklall - opened Jun 26, 2024

Discussion

ksooklall

Jun 26, 2024

I am trying to fine-tune CAPTIONS because the trained dataset isn't representative of the images I'm working with.
This is how I'm loading the model

def load_model():
    model_id = 'microsoft/Florence-2-large'
    revision = 'aec3bc57822662953317bc228d279bad98b7819c'#'refs/pr/6'
    model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True, revision=revision).to(cfg.device)
    processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True, revision=revision)
    return model, processor

And I copied the code from: https://huggingface.co/blog/finetune-florence2 and https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-finetune-florence-2-on-detection-dataset.ipynb?ref=blog.roboflow.com#scrollTo=bC06Mc7jOdpY to load the data. The issue I'm having is in the training script running the forward pass

            input_ids = inputs["input_ids"]
            pixel_values = inputs["pixel_values"]
            labels = processor.tokenizer(
                text=answers,
                return_tensors="pt",
                padding=True,
                return_token_type_ids=False
            ).input_ids.to(cfg.device)

            outputs = model(input_ids=input_ids, pixel_values=pixel_values, labels=labels)

  File "cache/models/modules/transformers_modules/microsoft/Florence-2-large/aec3bc57822662953317bc228d279bad98b7819c/modeling_florence2.py", line 2759, in forward
    return Florence2Seq2SeqLMOutput(
TypeError: __init__() got an unexpected keyword argument 'loss

I checked the file and the error is correct but when I add it there is another unexpected keyword arguement

ss22s

Jun 27, 2024

Try to refer to this issue: https://huggingface.co/microsoft/Florence-2-large/discussions/12#66752ee0ec54ee155826d156

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