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, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-4-reasoning-plus")
model = AutoModelForMultimodalLM.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 Settings

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
```

gugarosa commited on Jun 13, 2025

Commit

f1527a3

verified ·

1 Parent(s): f580375

fix(tokenizer_config): Sets fim and think tokens to non-special, and removes unk_token.

Browse files

Files changed (1) hide show

tokenizer_config.json +6 -15

tokenizer_config.json CHANGED Viewed

@@ -1,14 +1,6 @@
 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "5809": {
-      "content": "ï¿½",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
     "100256": {
       "content": "<|dummy_0|>",
       "lstrip": true,
@@ -31,7 +23,7 @@
       "normalized": false,
       "rstrip": true,
       "single_word": false,
-      "special": true
     },
     "100259": {
       "content": "<|fim_middle|>",
@@ -39,7 +31,7 @@
       "normalized": false,
       "rstrip": true,
       "single_word": false,
-      "special": true
     },
     "100260": {
       "content": "<|fim_suffix|>",
@@ -47,7 +39,7 @@
       "normalized": false,
       "rstrip": true,
       "single_word": false,
-      "special": true
     },
     "100261": {
       "content": "<|dummy_1|>",
@@ -767,7 +759,7 @@
       "normalized": false,
       "rstrip": true,
       "single_word": false,
-      "special": true
     },
     "100351": {
       "content": "</think>",
@@ -775,7 +767,7 @@
       "normalized": false,
       "rstrip": true,
       "single_word": false,
-      "special": true
     }
   },
   "bos_token": "<|endoftext|>",
@@ -786,6 +778,5 @@
   "model_max_length": 32768,
   "pad_token": "<|dummy_85|>",
   "padding_side": "left",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "ï¿½"
 }

 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "100256": {
       "content": "<|dummy_0|>",
       "lstrip": true,
       "normalized": false,
       "rstrip": true,
       "single_word": false,
+      "special": false
     },
     "100259": {
       "content": "<|fim_middle|>",
       "normalized": false,
       "rstrip": true,
       "single_word": false,
+      "special": false
     },
     "100260": {
       "content": "<|fim_suffix|>",
       "normalized": false,
       "rstrip": true,
       "single_word": false,
+      "special": false
     },
     "100261": {
       "content": "<|dummy_1|>",
       "normalized": false,
       "rstrip": true,
       "single_word": false,
+      "special": false
     },
     "100351": {
       "content": "</think>",
       "normalized": false,
       "rstrip": true,
       "single_word": false,
+      "special": false
     }
   },
   "bos_token": "<|endoftext|>",
   "model_max_length": 32768,
   "pad_token": "<|dummy_85|>",
   "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer"
 }