Instructions to use Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT with Transformers:

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

pipe = pipeline("text-generation", model="Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT")
model = AutoModelForCausalLM.from_pretrained("Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT")
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 Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT

SGLang

How to use Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT 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 "Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT" \
    --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": "Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT",
		"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 "Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT" \
        --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": "Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT with Docker Model Runner:
```
docker model run hf.co/Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT
```

MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy

This model is a fine-tuned version of Qwen3/Qwen3-1.7B on the MathSmith-HC shortCoT setting.

Check Details at https://github.com/Jasaxion/MathSmith

Dependence

Transformers 4.52.4
Pytorch 2.7.0+cu126
Datasets 3.6.0
Tokenizers 0.21.1

Citation

If you find this work useful, please cite:

@article{zhan2025mathsmith,
  title={MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy},
  author={Zhan, Shaoxiong and Lai, Yanlin and Lu, Ziyu and Lin, Dahua and Yang, Ziqing and Tan, Fei},
  journal={arXiv preprint arXiv:2508.05592},
  year={2025}
}

Downloads last month: 4

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Finetuned

(781)

this model

Datasets used to train Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT

Paper for Jasaxion/MathSmith-HC-Qwen3-1_7B-ShortCoT

MathSmith: Towards Extremely Hard Mathematical Reasoning by Forging Synthetic Problems with a Reinforced Policy

Paper • 2508.05592 • Published Aug 7, 2025 • 6