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

Libraries

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

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

pipe = pipeline("text-generation", model="microsoft/Phi-4-reasoning")
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")
model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-4-reasoning")
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 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"
# 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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

Gustavo de Rosa commited on May 8, 2025

Commit

57faa53

1 Parent(s): 34d6e8c

chore(root): Adds top_k information even if 50 is already the default.

Browse files

Files changed (2) hide show

README.md +2 -1
generation_config.json +1 -0

README.md CHANGED Viewed

@@ -56,7 +56,7 @@ library_name: transformers
 ## Usage
 > [!IMPORTANT]
-> To fully take advantage of the model's capabilities, inference must use `temperature=0.8`, `top_p=0.95`, and `do_sample=True`. For more complex queries, set `max_new_tokens=32768` to allow for longer chain-of-thought (CoT).
 ### Input Formats
@@ -88,6 +88,7 @@ outputs = model.generate(
     inputs.to(model.device),
     max_new_tokens=4096,
     temperature=0.8,
     top_p=0.95,
     do_sample=True,
 )

 ## Usage
 > [!IMPORTANT]
+> To fully take advantage of the model's capabilities, inference must use `temperature=0.8`, `top_k=50`, `top_p=0.95`, and `do_sample=True`. For more complex queries, set `max_new_tokens=32768` to allow for longer chain-of-thought (CoT).
 ### Input Formats
     inputs.to(model.device),
     max_new_tokens=4096,
     temperature=0.8,
+    top_k=50,
     top_p=0.95,
     do_sample=True,
 )

generation_config.json CHANGED Viewed

@@ -5,6 +5,7 @@
   "eos_token_id": 100265,
   "pad_token_id": 100349,
   "temperature": 0.8,
   "top_p": 0.95,
   "transformers_version": "4.51.1"
 }

   "eos_token_id": 100265,
   "pad_token_id": 100349,
   "temperature": 0.8,
+  "top_k": 50,
   "top_p": 0.95,
   "transformers_version": "4.51.1"
 }