Instructions to use netease-youdao/Confucius3-Math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use netease-youdao/Confucius3-Math with Transformers:

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

pipe = pipeline("text-generation", model="netease-youdao/Confucius3-Math")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("netease-youdao/Confucius3-Math")
model = AutoModelForCausalLM.from_pretrained("netease-youdao/Confucius3-Math")
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 netease-youdao/Confucius3-Math with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "netease-youdao/Confucius3-Math"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "netease-youdao/Confucius3-Math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/netease-youdao/Confucius3-Math

SGLang

How to use netease-youdao/Confucius3-Math 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 "netease-youdao/Confucius3-Math" \
    --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": "netease-youdao/Confucius3-Math",
		"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 "netease-youdao/Confucius3-Math" \
        --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": "netease-youdao/Confucius3-Math",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use netease-youdao/Confucius3-Math with Docker Model Runner:
```
docker model run hf.co/netease-youdao/Confucius3-Math
```

Add pipeline tag and link to paper

by nielsr HF Staff - opened Jun 26, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-6

Files changed (1) hide show

README.md +8 -6

README.md CHANGED Viewed

@@ -1,11 +1,12 @@
 ---
-license: mit
 language:
 - en
-base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
 tags:
 - chat
-library_name: transformers
 ---
 # Confucius3-Math
@@ -20,7 +21,7 @@ library_name: transformers
 <a href="https://github.com/netease-youdao/Confucius3-Math">🌟Github</a>
-<a href="https://github.com/netease-youdao/Confucius3-Math/blob/main/Confucius3-Math.pdf">🎓Paper</a>
 </div>
@@ -120,7 +121,8 @@ def parse_result_nostep(result):
     think_list = re.findall(think_pattern, result, re.DOTALL)
     assert len(think_list) == 1, \
-        f"The parsing results do not meet the expectations.\n{result}"
     think = think_list[0][0].strip()
     summary = think_list[0][1].strip()
@@ -139,4 +141,4 @@ If you find our work helpful, feel free to give us a cite.
    month = {June},
    year = {2025}
  }
-```

 ---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
 language:
 - en
+library_name: transformers
+license: mit
 tags:
 - chat
+pipeline_tag: text-generation
 ---
 # Confucius3-Math
 <a href="https://github.com/netease-youdao/Confucius3-Math">🌟Github</a>
+<a href="https://arxiv.org/abs/2506.18330">🎓Paper</a>
 </div>
     think_list = re.findall(think_pattern, result, re.DOTALL)
     assert len(think_list) == 1, \
+        f"The parsing results do not meet the expectations.
+{result}"
     think = think_list[0][0].strip()
     summary = think_list[0][1].strip()
    month = {June},
    year = {2025}
  }
+```