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

Libraries

How to use microsoft/Phi-4-reasoning-plus with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-4-reasoning-plus")
model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-4-reasoning-plus")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use microsoft/Phi-4-reasoning-plus with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/microsoft/Phi-4-reasoning-plus

SGLang

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

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

Inconsistency on AIME 24 benchmark

#15

by Jung - opened Jul 30, 2025

Discussion

Jung

Jul 30, 2025

Hi there are inconsistency in AIME 2024 results for phi4-reasoning-plus

in the paper, avg pass@1 is 81.3
in this blog https://www.microsoft.com/en-us/research/articles/phi-reasoning-once-again-redefining-what-is-possible-with-small-and-efficient-ai/
Figure 3, it can be read as 89.4

(Other numbers e.g. OmniMath and AIME25 are consistent)

Jung changed discussion title from Benchmark on AIME 24 to Inconsistencu on AIME 24 benchmark Jul 30, 2025

Jung changed discussion title from Inconsistencu on AIME 24 benchmark to Inconsistency on AIME 24 benchmark Jul 30, 2025

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