---
title: Qwen2-Math-7B-Instruct
canonical_url: "https://www.modelscope.cn/models/Qwen/Qwen2-Math-7B-Instruct"
md_url: "https://www.modelscope.cn/models/Qwen/Qwen2-Math-7B-Instruct.md"
repository: Qwen/Qwen2-Math-7B-Instruct
chinese_name: "千问2-数学-7B-Instruct"
last_updated: 2025-04-09
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
parameters: 7.6B
tensor_type:
  - BF16
library_name:
  - transformer
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 4375
stars: 3
tags:
  - chat
---

# Qwen2-Math-7B-Instruct

> Qwen2-Math-7B-Instruct - Qwen 在 ModelScope 开源的模型。Qwen2-Math 是一系列基于 Qwen2 LLM 构建的专门用于数学解题的语言模型，其数学能力显著超越了开源模型，甚至超过了闭源模型（如 GPT-4o）。我们希望Qwen2-Math能够为科学界解决需要复杂多步逻辑推理的高级数学问题做出贡献。

Qwen/Qwen2-Math-7B-Instruct 是 ModelScope 魔搭社区上的 7.6B 参数text-generation模型，采用 apache-2.0 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: Qwen/Qwen2-Math-7B-Instruct
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 7.6B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: chat
- **Downloads**: 4375
- **Stars**: 3
- **Last updated**: 2025-04-09

Source: https://www.modelscope.cn/models/Qwen/Qwen2-Math-7B-Instruct

---

# Qwen2-Math-7B-Instruct

> [!Warning]
> <div align="center">
> <b>
> 🚨 Temporarily this model mainly supports English. We will release bilingual (English & Chinese) models soon!
> </b>
> </div>

## Introduction

Over the past year, we have dedicated significant effort to researching and enhancing the reasoning capabilities of large language models, with a particular focus on their ability to solve arithmetic and mathematical problems. Today, we are delighted to introduce a serise of math-specific large language models of our Qwen2 series,  Qwen2-Math and Qwen2-Math-Instruct-1.5B/7B/72B. Qwen2-Math is a series of specialized math language models built upon the Qwen2 LLMs, which significantly outperforms the mathematical capabilities of open-source models and even closed-source models (e.g., GPT4o). We hope that Qwen2-Math can contribute to the scientific community for solving advanced mathematical problems that require complex, multi-step logical reasoning.


## Model Details


For more details, please refer to our [blog post](https://qwenlm.github.io/blog/qwen2-math/) and [GitHub repo](https://github.com/QwenLM/Qwen2-Math).


## Requirements
* `transformers>=4.40.0` for Qwen2-Math models. The latest version is recommended.

> [!Warning]
> <div align="center">
> <b>
> 🚨 This is a must because `transformers` integrated Qwen2 codes since `4.37.0`.
> </b>
> </div>

For requirements on GPU memory and the respective throughput, see similar results of Qwen2 [here](https://qwen.readthedocs.io/en/latest/benchmark/speed_benchmark.html).

## Quick Start

> [!Important]
>
> **Qwen2-Math-7B-Instruct** is an instruction model for chatting;
>
> **Qwen2-Math-7B** is a base model typically used for completion and few-shot inference, serving as a better starting point for fine-tuning.
> 

### 🤗 Hugging Face Transformers

Qwen2-Math can be deployed and inferred in the same way as [Qwen2](https://github.com/QwenLM/Qwen2). Here we show a code snippet to show you how to use the chat model with `transformers`:

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Qwen/Qwen2-Math-7B-Instruct"
device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Find the value of $x$ that satisfies the equation $4x+5 = 6x+7$."
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=512
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
```

### 🤖 ModelScope
We strongly advise users, especially those in mainland China, to use ModelScope. `snapshot_download` can help you solve issues concerning downloading checkpoints.


## Citation

If you find our work helpful, feel free to give us a citation.

```
@article{yang2024qwen2,
  title={Qwen2 technical report},
  author={Yang, An and Yang, Baosong and Hui, Binyuan and Zheng, Bo and Yu, Bowen and Zhou, Chang and Li, Chengpeng and Li, Chengyuan and Liu, Dayiheng and Huang, Fei and others},
  journal={arXiv preprint arXiv:2407.10671},
  year={2024}
}
```