Instructions to use AXCXEPT/phi-4-open-R1-Distill-EZOv1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AXCXEPT/phi-4-open-R1-Distill-EZOv1 with Transformers:

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

pipe = pipeline("text-generation", model="AXCXEPT/phi-4-open-R1-Distill-EZOv1", 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("AXCXEPT/phi-4-open-R1-Distill-EZOv1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("AXCXEPT/phi-4-open-R1-Distill-EZOv1", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AXCXEPT/phi-4-open-R1-Distill-EZOv1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AXCXEPT/phi-4-open-R1-Distill-EZOv1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AXCXEPT/phi-4-open-R1-Distill-EZOv1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AXCXEPT/phi-4-open-R1-Distill-EZOv1

SGLang

How to use AXCXEPT/phi-4-open-R1-Distill-EZOv1 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 "AXCXEPT/phi-4-open-R1-Distill-EZOv1" \
    --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": "AXCXEPT/phi-4-open-R1-Distill-EZOv1",
		"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 "AXCXEPT/phi-4-open-R1-Distill-EZOv1" \
        --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": "AXCXEPT/phi-4-open-R1-Distill-EZOv1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AXCXEPT/phi-4-open-R1-Distill-EZOv1 with Docker Model Runner:
```
docker model run hf.co/AXCXEPT/phi-4-open-R1-Distill-EZOv1
```

AXCXEPT commited on Jan 27, 2025

Commit

49d4c43

verified ·

1 Parent(s): 0e807ef

Update README.md

Browse files

Files changed (1) hide show

README.md +39 -1

README.md CHANGED Viewed

@@ -18,7 +18,45 @@ base_model:
 <!-- Provide a quick summary of what the model is/does. -->
 ## Model Details
-Deepseek-R1のDistill手法を模倣した、open-r1を採用して、phi-4モデルを Reasonerにしたモデルです。
 --------------------------------------
 ## HOW TO USE

 <!-- Provide a quick summary of what the model is/does. -->
 ## Model Details
+This model is a Reasoner version of the phi-4 model by employing open-r1, which mimics the Distill methodology of Deepseek-R1.
+(Deepseek-R1のDistill手法を模倣した、open-r1を採用して、phi-4モデルを Reasonerにしたモデルです)
+## Example Output
+```
+<thinking>
+まず、問題文を整理します。父親の現在の年齢は息子の3倍であり、6年前の父親の年齢は息子の5倍でした。これを数式で表現すると：
+1. 現在の年齢関係：父親の年齢 = 3 × 息子の年齢 → F = 3S
+2. 6年前の年齢関係：父親の年齢 - 6 = 5 × (息子の年齢 - 6) → F - 6 = 5(S - 6)
+これらの2つの方程式を同時に解きます。まず第1式からF = 3Sを代入すると：
+3S - 6 = 5(S - 6)
+3S - 6 = 5S - 30
+30 - 6 = 5S - 3S
+24 = 2S
+S = 12
+息子の年齢が12歳であることが分かります。これを第1式に代入すると：
+F = 3 × 12 = 36
+父親の年齢は36歳です。最後に条件を確認します：
+- 現在の年齢関係：36 = 3×12 → 成立
+- 6年前の年齢関係：36-6=30 vs 12-6=6 → 30=5×6 → 成立
+両方の条件が満たされているため、解は正しいと言えます。
+</thinking>
+<answer>
+父親の年齢は36歳、息子の年齢は12歳です。
+根拠：
+1. 現在の年齢関係：36 = 3×12（成立）
+2. 6年前の年齢関係：30 = 5×6（成立）
+3. 両方の条件を満たす唯一の解
+</answer>
+```
 --------------------------------------
 ## HOW TO USE