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

Libraries

How to use microsoft/Phi-3-vision-128k-instruct-onnx-cpu 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-onnx-cpu", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-vision-128k-instruct-onnx-cpu", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use microsoft/Phi-3-vision-128k-instruct-onnx-cpu 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-onnx-cpu"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/Phi-3-vision-128k-instruct-onnx-cpu",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use microsoft/Phi-3-vision-128k-instruct-onnx-cpu 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-onnx-cpu" \
    --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/Phi-3-vision-128k-instruct-onnx-cpu",
		"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/Phi-3-vision-128k-instruct-onnx-cpu" \
        --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/Phi-3-vision-128k-instruct-onnx-cpu",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

configuration_phi3_v.py

by claytonOps - opened Jun 3, 2024

Discussion

claytonOps

Jun 3, 2024

I have tried using the ONNX docs as guidance, but i keep receiving the following error when running the model. thanks for any help or thoughts.

error:
microsoft/Phi-3-vision-128k-instruct-onnx-cpu does not appear to have a file named configuration_phi3_v.py. Checkout 'https://huggingface.co/microsoft/Phi-3-vision-128k-instruct-onnx-cpu/tree/main' for available files.

kvaishnavi

Microsoft org Jun 4, 2024

Are you following the Phi-3 vision ONNX tutorial to run with ONNX Runtime GenAI? If so, which step is raising this error? The published ONNX tutorial should not require configuration_phi3_v.py.

claytonOps

Jul 23, 2024

@kvaishnavi , yes i am following the ONNX tutorial.

I haven't dug into the issue in a minute to get the exact step.

nostorian

Jul 27, 2024

using transformers here getting the same issue. @claytonOps @kvaishnavi any solutions?

Azhuvath

Jul 30, 2024

Does the below code work?

Load model directly

from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-vision-128k-instruct-onnx-cpu", trust_remote_code=True)

kvaishnavi

Microsoft org Jul 30, 2024

Does the below code work?

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

Hugging Face's Transformers library only works with PyTorch models and not ONNX models so this code will not work. The uploaded Phi-3 vision ONNX models work with ONNX Runtime GenAI. You can follow the Phi-3 vision ONNX tutorial to run the ONNX models.

yanggzgzg

Aug 12, 2024

或者你可以直接下载这里的脚本来推理onnx https://github.com/microsoft/onnxruntime-genai/blob/main/examples/python/phi3v.py

kvaishnavi changed discussion status to closed Sep 14, 2024

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