Instructions to use XINLI1997/WirelessMathLM-0.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use XINLI1997/WirelessMathLM-0.5B with Transformers:

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

pipe = pipeline("text-generation", model="XINLI1997/WirelessMathLM-0.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("XINLI1997/WirelessMathLM-0.5B")
model = AutoModelForCausalLM.from_pretrained("XINLI1997/WirelessMathLM-0.5B", 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/WirelessMathLM-0.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XINLI1997/WirelessMathLM-0.5B"
# 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/WirelessMathLM-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XINLI1997/WirelessMathLM-0.5B

SGLang

How to use XINLI1997/WirelessMathLM-0.5B 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/WirelessMathLM-0.5B" \
    --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/WirelessMathLM-0.5B",
		"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/WirelessMathLM-0.5B" \
        --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/WirelessMathLM-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use XINLI1997/WirelessMathLM-0.5B with Docker Model Runner:
```
docker model run hf.co/XINLI1997/WirelessMathLM-0.5B
```

WirelessMathLM-0.5B

GRPO-trained reference checkpoint from WirelessMathBench-XL: An Auditable Benchmark for Wireless Mathematical Reasoning (NeurIPS 2026, Evaluations and Datasets Track).

Project page · arXiv · OpenReview · Code · Dataset

Model

Base: Qwen/Qwen2.5-0.5B. Initialised from the Qwen2.5-0.5B base checkpoint (no SFT warm-start).
Training: GRPO with EasyR1 on the WirelessMathBench-XL train split (3,227 problems), 40 epochs / 240 steps, composite reward 0.1 × format + 0.9 × verifier accuracy, AdamW (lr 1e-6, cosine), KL coefficient 0.01, 4 × NVIDIA A6000. See Appendix B of the paper.
Precision: bfloat16.

Results

Evaluation (WirelessMathBench-XL test)	Accuracy
Full 800-item test split (paper Tab. 3, row D14)	2.12%
310-item public test subset (paper Appendix L)	2.26%

Locked protocol: 2k-token answer budget, T = 0.6, hierarchical verifier (deterministic match, canonicalisation, GPT-4.1-mini fallback judge).

Training-time check under greedy model selection (paper Tab. 7): base 13.38% → GRPO 14.87%. These values use a different protocol from the locked scores.

Usage

The paper queries these checkpoints through a raw completion endpoint (no chat template), using the dataset's prompt field.

from datasets import load_dataset
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "XINLI1997/WirelessMathLM-0.5B"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="auto", device_map="auto")

ex = load_dataset("XINLI1997/WirelessMATHBench-XL", "cc_by", split="test")[0]
prompt = ex["prompt"]
inputs = tok(prompt, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=2048, do_sample=True, temperature=0.6)
print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Limitations

These are release-split learnability checks, not evidence of general or verifier-independent reasoning. The train/test split is problem-level, so train and test share source papers.
The reward verifier and the evaluation fallback share the same checkpoint family and prompt style.
Intended for research on wireless mathematical reasoning; not a general-purpose assistant.
The 0.5B checkpoint stays near the floor on the locked protocol and is included for completeness.

License

Apache 2.0, following the base model.

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}
}