Instructions to use Source82/florence-2-base-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Source82/florence-2-base-4bit with Transformers:

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

pipe = pipeline("image-text-to-text", model="Source82/florence-2-base-4bit", trust_remote_code=True)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Source82/florence-2-base-4bit", trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained("Source82/florence-2-base-4bit", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Source82/florence-2-base-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Source82/florence-2-base-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Source82/florence-2-base-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Source82/florence-2-base-4bit

SGLang

How to use Source82/florence-2-base-4bit 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 "Source82/florence-2-base-4bit" \
    --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": "Source82/florence-2-base-4bit",
		"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 "Source82/florence-2-base-4bit" \
        --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": "Source82/florence-2-base-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Source82/florence-2-base-4bit with Docker Model Runner:
```
docker model run hf.co/Source82/florence-2-base-4bit
```

Source82 commited on Mar 11, 2025

Commit

0be0c1e

verified ·

1 Parent(s): 6ebfee1

Update config.json

Browse files

Files changed (1) hide show

config.json +1 -1

config.json CHANGED Viewed

@@ -177,7 +177,7 @@
     "length_penalty": 1.0,
     "max_length": 20,
     "min_length": 0,
-    "model_type": "",
     "no_repeat_ngram_size": 0,
     "num_beam_groups": 1,
     "num_beams": 1,

     "length_penalty": 1.0,
     "max_length": 20,
     "min_length": 0,
+    "model_type": "davit",
     "no_repeat_ngram_size": 0,
     "num_beam_groups": 1,
     "num_beams": 1,