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

vLLM

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

SGLang

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
```

haipingwu commited on Jul 19, 2024

Commit

af7d34c

1 Parent(s): f2be9b1

update model init with float16

Browse files

Files changed (2) hide show

README.md +9 -5
config.json +1 -1

README.md CHANGED Viewed

@@ -27,7 +27,7 @@ Resources and Technical Documentation:
 ## How to Get Started with the Model
-Use the code below to get started with the model.
 ```python
 import requests
@@ -35,8 +35,10 @@ import requests
 from PIL import Image
 from transformers import AutoProcessor, AutoModelForCausalLM
-model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-base-ft", trust_remote_code=True)
 processor = AutoProcessor.from_pretrained("microsoft/Florence-2-base-ft", trust_remote_code=True)
 prompt = "<OD>"
@@ -44,7 +46,7 @@ prompt = "<OD>"
 url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
 image = Image.open(requests.get(url, stream=True).raw)
-inputs = processor(text=prompt, images=image, return_tensors="pt")
 generated_ids = model.generate(
     input_ids=inputs["input_ids"],
@@ -77,8 +79,10 @@ import requests
 from PIL import Image
 from transformers import AutoProcessor, AutoModelForCausalLM
-model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-base-ft", trust_remote_code=True)
 processor = AutoProcessor.from_pretrained("microsoft/Florence-2-base-ft", trust_remote_code=True)
 url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
@@ -89,7 +93,7 @@ def run_example(task_prompt, text_input=None):
         prompt = task_prompt
     else:
         prompt = task_prompt + text_input
-    inputs = processor(text=prompt, images=image, return_tensors="pt")
     generated_ids = model.generate(
       input_ids=inputs["input_ids"],
       pixel_values=inputs["pixel_values"],

 ## How to Get Started with the Model
+Use the code below to get started with the model.  All models are trained with float16.
 ```python
 import requests
 from PIL import Image
 from transformers import AutoProcessor, AutoModelForCausalLM
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-base-ft", torch_dtype=torch_dtype, trust_remote_code=True).to(device)
 processor = AutoProcessor.from_pretrained("microsoft/Florence-2-base-ft", trust_remote_code=True)
 prompt = "<OD>"
 url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
 image = Image.open(requests.get(url, stream=True).raw)
+inputs = processor(text=prompt, images=image, return_tensors="pt").to(device, torch_dtype)
 generated_ids = model.generate(
     input_ids=inputs["input_ids"],
 from PIL import Image
 from transformers import AutoProcessor, AutoModelForCausalLM
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-base-ft", torch_dtype=torch_dtype, trust_remote_code=True).to(device)
 processor = AutoProcessor.from_pretrained("microsoft/Florence-2-base-ft", trust_remote_code=True)
 url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
         prompt = task_prompt
     else:
         prompt = task_prompt + text_input
+    inputs = processor(text=prompt, images=image, return_tensors="pt").to(device, torch_dtype)
     generated_ids = model.generate(
       input_ids=inputs["input_ids"],
       pixel_values=inputs["pixel_values"],

config.json CHANGED Viewed

@@ -79,7 +79,7 @@
     "image_feature_source": ["spatial_avg_pool", "temporal_avg_pool"]
   },
   "vocab_size": 51289,
-  "torch_dtype": "float32",
   "transformers_version": "4.41.0.dev0",
   "is_encoder_decoder": true
 }

     "image_feature_source": ["spatial_avg_pool", "temporal_avg_pool"]
   },
   "vocab_size": 51289,
+  "torch_dtype": "float16",
   "transformers_version": "4.41.0.dev0",
   "is_encoder_decoder": true
 }