Instructions to use youngzhong/SOD-1.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use youngzhong/SOD-1.7B with Transformers:

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

pipe = pipeline("text-generation", model="youngzhong/SOD-1.7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("youngzhong/SOD-1.7B")
model = AutoModelForCausalLM.from_pretrained("youngzhong/SOD-1.7B")
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-1.7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "youngzhong/SOD-1.7B"
# 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-1.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/youngzhong/SOD-1.7B

SGLang

How to use youngzhong/SOD-1.7B 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-1.7B" \
    --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-1.7B",
		"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-1.7B" \
        --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-1.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use youngzhong/SOD-1.7B with Docker Model Runner:
```
docker model run hf.co/youngzhong/SOD-1.7B
```

SOD-1.7B / README.md

youngzhong

Upload README.md with huggingface_hub

232c6fc verified about 17 hours ago

preview code

raw

history blame contribute delete

3.6 kB

	---
	language:
	- en
	license: apache-2.0
	library_name: transformers
	base_model: Qwen/Qwen3-1.7B
	tags:
	- agent
	- tool-use
	- distillation
	- math
	- code
	- reasoning
	pipeline_tag: text-generation
	---

	<div align="center">

	<h1>SOD-1.7B</h1>

	<p>
	<a href="https://arxiv.org/abs/2605.07725">
	<img src="https://img.shields.io/badge/Paper-Arxiv-red?logo=arxiv&logoColor=red" alt="Paper on arXiv"/>
	</a>
	<a href="https://github.com/YoungZ365/SOD">
	<img src="https://img.shields.io/badge/Code-GitHub-black?logo=github&logoColor=white" alt="Code on GitHub"/>
	</a>
	<a href="https://huggingface.co/collections/youngzhong/sod-6a03530369d76913c24a4ffb">
	<img src="https://img.shields.io/badge/Collection-SOD-yellow?logo=huggingface" alt="HuggingFace Collection"/>
	</a>
	</p>

	</div>

	## About

	SOD-1.7B is a 1.7B student model distilled from a 4B teacher using SOD (Step-wise On-policy Distillation), a method designed for training small language model agents with tool-integrated reasoning capabilities.

	SOD addresses the cascading error propagation problem in on-policy distillation for agentic reasoning by introducing an adaptive step-level weighting mechanism that suppresses distillation loss on drifted steps and restores supervision when the student recovers alignment — all at negligible additional computational cost.

	## Model Information

	\| Attribute \| Value \|
	\|-----------\|-------\|
	\| Base Model \| [Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) \|
	\| Teacher Model \| [SOD-GRPO_teacher-4B](https://huggingface.co/youngzhong/SOD-GRPO_teacher-4B) \|
	\| Training Pipeline \| Cold-Start SFT → SOD (Step-wise On-policy Distillation) \|
	\| Parameters \| 1.7B \|

	## Related Models

	\| Model \| Description \|
	\|-------\|-------------\|
	\| [SOD-0.6B](https://huggingface.co/youngzhong/SOD-0.6B) \| SOD-distilled 0.6B student \|
	\| [SOD-1.7B](https://huggingface.co/youngzhong/SOD-1.7B) \| SOD-distilled 1.7B student (this model) \|
	\| [SOD-GRPO_teacher-4B](https://huggingface.co/youngzhong/SOD-GRPO_teacher-4B) \| GRPO-trained 4B teacher model \|

	## Performance

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

	### 1.7B Student Results

	\| Method \| AIME 2024 \| AIME 2025 \| GPQA-Diamond \| LiveCodeBench-v6 \| Average \|
	\|--------\|-----------\|-----------\|--------------\|------------------\|---------\|
	\| Vanilla \| 9.90 \| 8.96 \| 26.80 \| 22.73 \| 17.10 \|
	\| SFT \| 26.77 \| 22.40 \| 29.85 \| 24.63 \| 25.91 \|
	\| GRPO \| 25.63 \| 21.67 \| 33.55 \| 20.70 \| 25.39 \|
	\| OPD \| 43.86 \| 37.04 \| 31.73 \| 32.45 \| 36.27 \|
	\| OPSD_gt \| 33.85 \| 24.69 \| 35.02 \| 22.73 \| 29.07 \|
	\| OPSD_hint \| 34.42 \| 21.43 \| 33.46 \| 23.12 \| 28.11 \|
	\| SOD (This Model) \| 50.83 \| 41.72 \| 38.72 \| 40.63 \| 42.98 \|

	### Teacher Model (4B)

	\| Method \| AIME 2024 \| AIME 2025 \| GPQA-Diamond \| LiveCodeBench-v6 \| Average \|
	\|--------\|-----------\|-----------\|--------------\|------------------\|---------\|
	\| GRPO \| 67.60 \| 60.42 \| 55.19 \| 63.13 \| 61.59 \|

	## Key Highlights

	- 🏆 Recovers 69.8% of teacher performance with only 1.7B parameters (42.98 vs 61.59)
	- 📈 +18.5% over second-best baseline (OPD) on average
	- 💡 Minimal extra compute: The divergence metric reuses log-probabilities already computed in the forward pass

	## Citation

	```bibtex
	@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}
	}
	```