Instructions to use RoadQAQ/Qwen2.5-Math-7B-16k-think with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RoadQAQ/Qwen2.5-Math-7B-16k-think with Transformers:

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

pipe = pipeline("text-generation", model="RoadQAQ/Qwen2.5-Math-7B-16k-think")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RoadQAQ/Qwen2.5-Math-7B-16k-think")
model = AutoModelForCausalLM.from_pretrained("RoadQAQ/Qwen2.5-Math-7B-16k-think", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RoadQAQ/Qwen2.5-Math-7B-16k-think with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RoadQAQ/Qwen2.5-Math-7B-16k-think"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RoadQAQ/Qwen2.5-Math-7B-16k-think",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RoadQAQ/Qwen2.5-Math-7B-16k-think

SGLang

How to use RoadQAQ/Qwen2.5-Math-7B-16k-think 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 "RoadQAQ/Qwen2.5-Math-7B-16k-think" \
    --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": "RoadQAQ/Qwen2.5-Math-7B-16k-think",
		"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 "RoadQAQ/Qwen2.5-Math-7B-16k-think" \
        --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": "RoadQAQ/Qwen2.5-Math-7B-16k-think",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RoadQAQ/Qwen2.5-Math-7B-16k-think with Docker Model Runner:
```
docker model run hf.co/RoadQAQ/Qwen2.5-Math-7B-16k-think
```

The base Qwen2.5-Math-7B model used by ReLIFT. We change to rope_theta from 10000 to 40000 and extend the context window to 16k. Also, we modify the chat_template for the system prompt and add .

Github: https://github.com/TheRoadQaQ/ReLIFT

Citation

If you find our model, data, or evaluation code useful, please kindly cite our paper:

@article{ma2025learning,
  title={Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions},
  author={Ma, Lu and Liang, Hao and Qiang, Meiyi and Tang, Lexiang and Ma, Xiaochen and Wong, Zhen Hao and Niu, Junbo and Shen, Chengyu and He, Runming and Cui, Bin and others},
  journal={arXiv preprint arXiv:2506.07527},
  year={2025}
}

Downloads last month: 35

Safetensors

Model size

8B params

Tensor type

F32

Collection including RoadQAQ/Qwen2.5-Math-7B-16k-think

ReLIFT

Collection

ReLIFT, a training method that interleaves RL with online FT, achieving superior performance and efficiency compared to using RL or SFT alone. • 8 items • Updated Jun 10, 2025 • 1

Paper for RoadQAQ/Qwen2.5-Math-7B-16k-think

Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions

Paper • 2506.07527 • Published Jun 9, 2025 • 3