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 Settings

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
```

Is JSON mode available in the Phi-3-vision API

#55

by gaurav646 - opened Jul 25, 2024

Discussion

gaurav646

Jul 25, 2024

Hi all, I tried explicitly mentioning regarding the output format in JSON and also to avoid any other information apart from it.
but, looks like phi3-vision doesn't respect much about the output format.

Do we have a output mode like json as available in GPT-4 API.

2U1

Jul 25, 2024

@gaurav646 I was having the same issue with you. However I noticed Phi3-mini just shows bad performance at formatting the output in json.
You can see at here https://huggingface.co/microsoft/Phi-3-mini-128k-instruct json foratting showing bad performance.
I'm using XML formatting for the alternative way and it is much better now.

gaurav646

Jul 25, 2024

Got it. You ask for the output in the xaml format. And the format is coming consistent.
I will try that.

2U1

Jul 25, 2024

@gaurav646 Yes I'm using something like this

prompt_for_llm = (
    "Provide all necessary information in the report and it should be filled in a XML format with the options below:\n"
    "<report>\n"
    "  <category>[Construction/Flood/Congestion/Normal]</category>\n"
    "  <weather>[Clear/Overcast/Snow/Rain]</weather>\n"
    "  <level>[Danger/Caution/Safe]</level>\n"
    "  <detail>[detailed description of the situation]</detail>\n"
    "</report>"
)

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