Instructions to use microsoft/Phi-4-mini-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/Phi-4-mini-instruct with Transformers:

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

pipe = pipeline("text-generation", model="microsoft/Phi-4-mini-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-4-mini-instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-4-mini-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use microsoft/Phi-4-mini-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/Phi-4-mini-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-4-mini-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/microsoft/Phi-4-mini-instruct

SGLang

How to use microsoft/Phi-4-mini-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-4-mini-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-4-mini-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-4-mini-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-4-mini-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use microsoft/Phi-4-mini-instruct with Docker Model Runner:
```
docker model run hf.co/microsoft/Phi-4-mini-instruct
```

Output is incohesive

#33

by kirkiarty - opened Jun 23, 2025

Discussion

kirkiarty

Jun 23, 2025

The output is incohesive and wrong, I thought it corrupted or something, redownloaded, nothing changed

I'm using pipeline, updated transformers today
pipe = pipeline("text-generation", model=model, torch_dtype=torch.bfloat16, device_map="auto", pad_token_id=0)
pipe(messages, max_new_tokens=1000, do_sample=True, temperature=0.5, repetition_penalty=1.18)

toastertech

Jul 5, 2025

repetition penalty may be too high

kirkiarty

Jul 5, 2025

repetition penalty may be too high

Doesn't seem to change with penalty

brentrynn

Jul 6, 2025

There is a couple things you need to do. First off you should make your sending in the proper prompts with system commands. The other issue is phi really doesn't play well with the huggingface templates for chat. What that means is you get extra garbage in your chats. My suggestion is use the ONNX model or convert this one to ONNX and use my scripts to fix the build. Once when you do this the model works well.

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