Instructions to use arjunanand13/Florence-enphase2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arjunanand13/Florence-enphase2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="arjunanand13/Florence-enphase2", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("arjunanand13/Florence-enphase2", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("arjunanand13/Florence-enphase2", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use arjunanand13/Florence-enphase2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arjunanand13/Florence-enphase2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arjunanand13/Florence-enphase2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/arjunanand13/Florence-enphase2

SGLang

How to use arjunanand13/Florence-enphase2 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 "arjunanand13/Florence-enphase2" \
    --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": "arjunanand13/Florence-enphase2",
		"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 "arjunanand13/Florence-enphase2" \
        --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": "arjunanand13/Florence-enphase2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use arjunanand13/Florence-enphase2 with Docker Model Runner:
```
docker model run hf.co/arjunanand13/Florence-enphase2
```

arjunanand13 commited on Oct 11, 2024

Commit

54b2a68

verified ·

1 Parent(s): 23f8a2f

Update handler.py

Browse files

Files changed (1) hide show

handler.py +14 -0

handler.py CHANGED Viewed

@@ -1,3 +1,17 @@
 from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM, pipeline
 class InferenceHandler:

+import subprocess
+import sys
+def install(package):
+    subprocess.check_call([sys.executable, "-m", "pip", "install", package])
+try:
+    install("flash_attn")
+except subprocess.CalledProcessError:
+    print("Failed to install flash_attn")
+install("timm")
+install("einops")
 from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM, pipeline
 class InferenceHandler: