Wizardmath 7B V1.1

🚀 WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct (RLEIF)

WizardMath enhances large language models' mathematical reasoning capabilities through Reinforced Evol-Instruct (RLEIF).

🏠 Home Page

🤗 HF Repo •🐱 Github Repo • 🐦 Twitter

📃 [WizardLM] • 📃 [WizardCoder] • 📃 [WizardMath]

👋 Join our Discord

✨ Features

News

• [12/19/2023] 🔥 We released WizardMath-7B-V1.1 trained from Mistral-7B, the SOTA 7B math LLM, achieving 83.2 pass@1 on GSM8k, and 33.0 pass@1 on MATH. Use this [Demo] to chat with it.
• [12/19/2023] 🔥 WizardMath-7B-V1.1 outperforms ChatGPT 3.5, Gemini Pro, Mixtral MOE, and Claude Instant on GSM8K pass@1.
• [12/19/2023] 🔥 WizardMath-7B-V1.1 is comparable with ChatGPT 3.5, Gemini Pro, and surpasses Mixtral MOE on MATH pass@1.

Model Comparison Tables

Model Performance Overview

Comparison with Open Source 7B Size Math LLMs (12/19/2023)

Comparison with Large Open Source (30B~70B) LLMs (12/19/2023)

🔧 Technical Details

Data Contamination Check

Before model training, we carefully and rigorously checked all the training data, and used multiple deduplication methods to verify and prevent data leakage on GSM8k and MATH test set.

Model System Prompts

⚠️ Important Note

Please use the same systems prompts strictly with us, and we do not guarantee the accuracy of the quantified versions.

Default Version

"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"

CoT Version

💡 Usage Tip

For the simple math questions, we do NOT recommend to use the CoT prompt.

"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response: Let's think step by step."

💻 Usage Examples

Inference WizardMath Demo Script

We provide the WizardMath inference demo code here.

📄 License

Citation

Please cite the repo if you use the data, method or code in this repo.

@article{luo2023wizardmath,
  title={WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct},
  author={Luo, Haipeng and Sun, Qingfeng and Xu, Can and Zhao, Pu and Lou, Jianguang and Tao, Chongyang and Geng, Xiubo and Lin, Qingwei and Chen, Shifeng and Zhang, Dongmei},
  journal={arXiv preprint arXiv:2308.09583},
  year={2023}
}