Instructions to use microsoft/Phi-3-vision-128k-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/Phi-3-vision-128k-instruct with Transformers:

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

pipe = pipeline("text-generation", model="microsoft/Phi-3-vision-128k-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-vision-128k-instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use microsoft/Phi-3-vision-128k-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/Phi-3-vision-128k-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Phi-3-vision-128k-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/microsoft/Phi-3-vision-128k-instruct

SGLang

How to use microsoft/Phi-3-vision-128k-instruct 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/Phi-3-vision-128k-instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Phi-3-vision-128k-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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/Phi-3-vision-128k-instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Phi-3-vision-128k-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use microsoft/Phi-3-vision-128k-instruct with Docker Model Runner:
```
docker model run hf.co/microsoft/Phi-3-vision-128k-instruct
```

inference and generation runtime - how to reduce latency

#38

by wamozart - opened Jun 13, 2024

Discussion

wamozart

Jun 13, 2024

Hi all,

This is a great model but I was wondering how can I speed up the inference time. My app is running such that it accepts two image + text and create a comparison of them.

Running on EC2 g4.2xl, inference and response time is about 5-6 seconds. I've tried a new generation gpu (H family) but didn't see any improvements (which is kind of weird). I also tried to load in 4bit but had some issues. The only improvement I saw is when I used onnxruntime-genai, (https://huggingface.co/microsoft/Phi-3-vision-128k-instruct-onnx-cuda) but unfortunately, the implementation doesn't allow multiple images as inputs.

Would be happy for your suggestions.

Tnx

ali-hagrassy

Jan 14, 2025

try https://huggingface.co/microsoft/Phi-3.5-vision-instruct-onnx/tree/main/gpu/gpu-int4-rtn-block-32, the model supports multiple images

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