Instructions to use XINLI1997/Math12k-GRPO-Control-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XINLI1997/Math12k-GRPO-Control-7B with Transformers:

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

pipe = pipeline("text-generation", model="XINLI1997/Math12k-GRPO-Control-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("XINLI1997/Math12k-GRPO-Control-7B")
model = AutoModelForCausalLM.from_pretrained("XINLI1997/Math12k-GRPO-Control-7B", device_map="auto")
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 Settings

vLLM

How to use XINLI1997/Math12k-GRPO-Control-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XINLI1997/Math12k-GRPO-Control-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": "XINLI1997/Math12k-GRPO-Control-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XINLI1997/Math12k-GRPO-Control-7B

SGLang

How to use XINLI1997/Math12k-GRPO-Control-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 "XINLI1997/Math12k-GRPO-Control-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": "XINLI1997/Math12k-GRPO-Control-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 "XINLI1997/Math12k-GRPO-Control-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": "XINLI1997/Math12k-GRPO-Control-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use XINLI1997/Math12k-GRPO-Control-7B with Docker Model Runner:
```
docker model run hf.co/XINLI1997/Math12k-GRPO-Control-7B
```

Math12k-GRPO-Control-7B

Size- and step-budget-matched general-math GRPO control from WirelessMathBench-XL: An Auditable Benchmark for Wireless Mathematical Reasoning (NeurIPS 2026, Evaluations and Datasets Track). It is the comparison point for WirelessMathLM-7B, not a wireless-math model.

Project page · arXiv · OpenReview · Code · Dataset

Model

Base: Qwen/Qwen2.5-7B base checkpoint (no SFT warm-start).
Training data: 3,227 problems sampled from hiyouga/math12k (train split, seed 20260501), matching the size of the WirelessMathBench-XL train split.
Training: EasyR1 GRPO, 40 epochs / 240 steps, format weight 0.1, same budget as WirelessMathLM-7B. Lower-level batch settings, prompt template, and reward implementation are not identical to the WirelessMathLM runs, so this is not a one-variable causal ablation.
Precision: bfloat16.

Results on WirelessMathBench-XL (800-item test split)

Model	Accuracy
Math12k-GRPO-Control-7B (this model)	22.75% (182/800)
WirelessMathLM-7B	47.88% (383/800)

Paired problem-level bootstrap (10,000 resamples, seed 0): control − WirelessMathLM-7B = −25.13 pp, 95% CI [−29.00, −21.13]. One training run per condition, so the interval reflects test-item resampling, not training-seed variation. Protocol: raw completion endpoint, 2,048-token answer budget, T = 0.6, hierarchical verifier with GPT-4.1-mini fallback.

This supports domain-aligned learnability on the release split only. It does not establish intrinsic difficulty of wireless mathematics, a causal isolation of wireless constraints, or paper-disjoint generalisation (the release split shares source papers between train and test).

Citation

@inproceedings{
li2026wirelessmathbenchxl,
title={WirelessMathBench-XL: An Auditable Benchmark for Wireless Mathematical Reasoning},
author={Xin Li and Mengbing Liu and Yiyang Zhu and Wenhe Zhang and Li Wei and Jiancheng An and Chau Yuen},
booktitle={The Fortieth Annual Conference on Neural Information Processing Systems Evaluations and Datasets Track},
year={2026}
}