metadata
license: llama2
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
🤗 HF Repo • 🐦 Twitter • 📃 [WizardLM] • 📃 [WizardCoder]
👋 Join our Discord
| Model | Checkpoint | Paper | GSM8k | MATH | License |
|---|---|---|---|---|---|
| WizardMath-70B-V1.0 | 🤗 HF Link | 📃Coming Soon | 81.6 | 22.7 | Llama 2 License |
| WizardMath-13B-V1.0 | 🤗 HF Link | 📃Coming Soon | 63.9 | 14.0 | Llama 2 License |
| WizardMath-7B-V1.0 | 🤗 HF Link | 📃Coming Soon | 54.9 | 10.7 | Llama 2 License |
Github Repo: https://github.com/nlpxucan/WizardLM/tree/main/WizardMath
Twitter:
Discord: https://discord.gg/bpmeZD7V
❗Note for model system prompts usage:
CoT Version:
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{instruction}
### Response: Let's think step by step.
❗To commen concern about dataset:
Recently, there have been clear changes in the open-source policy and regulations of our overall organization's code, data, and models. Despite this, we have still worked hard to obtain opening the weights of the model first, but the data involves stricter auditing and is in review with our legal team . Our researchers have no authority to publicly release them without authorization. Thank you for your understanding.