Instructions to use youngzhong/SOD-GRPO_teacher-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use youngzhong/SOD-GRPO_teacher-4B with Transformers:

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

pipe = pipeline("text-generation", model="youngzhong/SOD-GRPO_teacher-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("youngzhong/SOD-GRPO_teacher-4B")
model = AutoModelForCausalLM.from_pretrained("youngzhong/SOD-GRPO_teacher-4B")
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 youngzhong/SOD-GRPO_teacher-4B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/youngzhong/SOD-GRPO_teacher-4B

SGLang

How to use youngzhong/SOD-GRPO_teacher-4B 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 "youngzhong/SOD-GRPO_teacher-4B" \
    --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": "youngzhong/SOD-GRPO_teacher-4B",
		"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 "youngzhong/SOD-GRPO_teacher-4B" \
        --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": "youngzhong/SOD-GRPO_teacher-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use youngzhong/SOD-GRPO_teacher-4B with Docker Model Runner:
```
docker model run hf.co/youngzhong/SOD-GRPO_teacher-4B
```

SOD-GRPO_teacher-4B

About

SOD-GRPO_teacher-4B is a 4B agentic reasoning model trained with GRPO (Group Relative Policy Optimization), serving as the teacher model in the SOD distillation framework.

This model is used to distill smaller student models (SOD-0.6B and SOD-1.7B) via the SOD method, which introduces adaptive step-level weighting to handle cascading error propagation in tool-integrated reasoning.

Model Information

Attribute	Value
Base Model	Qwen3-4B
Training Pipeline	Cold-Start SFT → GRPO
Parameters	4B

Related Models

Model	Description
SOD-0.6B	SOD-distilled 0.6B student
SOD-1.7B	SOD-distilled 1.7B student
SOD-GRPO_teacher-4B	GRPO-trained 4B teacher model (this model)

Performance

We report average@32 over 5 runs on challenging math, science, and code benchmarks.

Method	AIME 2024	AIME 2025	GPQA-Diamond	LiveCodeBench-v6	Average
GRPO (This Model)	67.60	60.42	55.19	63.13	61.59

Distilled Students

Model	AIME 2024	AIME 2025	GPQA-Diamond	LiveCodeBench-v6	Average
SOD-0.6B	20.84	26.13	22.19	27.72	24.22
SOD-1.7B	50.83	41.72	38.72	40.63	42.98

Acknowledgement

We sincerely thank the authors of DemyAgent-4B and the paper "Demystifying Reinforcement Learning in Agentic Reasoning" (arXiv:2510.11701) for their contribution.

Citation

@article{zhong2026sod,
      title={SOD: Step-wise On-policy Distillation for Small Language Model Agents}, 
      author={Qiyong Zhong and Mao Zheng and Mingyang Song and Xin Lin and Jie Sun and Houcheng Jiang and Xiang Wang and Junfeng Fang},
      journal={arXiv preprint arXiv:2605.07725},
      year={2026}
}