Update README.md
Browse files
README.md
CHANGED
|
@@ -6,4 +6,75 @@ license_link: https://huggingface.co/WizardLM/WizardMath-7B-V1.1/resolve/main/LI
|
|
| 6 |
language:
|
| 7 |
- en
|
| 8 |
pipeline_tag: text-generation
|
| 9 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
language:
|
| 7 |
- en
|
| 8 |
pipeline_tag: text-generation
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct (RLEIF)
|
| 13 |
+
|
| 14 |
+
<p style="font-size:28px;" align="center">
|
| 15 |
+
π <a href="https://wizardlm.github.io/" target="_blank">Home Page</a> </p>
|
| 16 |
+
<p align="center">
|
| 17 |
+
<p align="center">
|
| 18 |
+
π€ <a href="https://huggingface.co/WizardLM" target="_blank">HF Repo</a> β’π± <a href="https://github.com/nlpxucan/WizardLM" target="_blank">Github Repo</a> β’ π¦ <a href="https://twitter.com/WizardLM_AI" target="_blank">Twitter</a> β’ π <a href="https://arxiv.org/abs/2304.12244" target="_blank">[WizardLM]</a> β’ π <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> β’ π <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a> <br>
|
| 19 |
+
</p>
|
| 20 |
+
<p align="center">
|
| 21 |
+
π Join our <a href="https://discord.gg/VZjjHtWrKs" target="_blank">Discord</a>
|
| 22 |
+
</p>
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
| Model | Checkpoint | Paper | GSM8k | MATH |Online Demo| License|
|
| 27 |
+
| ----- |------| ---- |------|-------| ----- | ----- |
|
| 28 |
+
| **WizardMath-7B-V1.0** | π€ <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.1" target="_blank">HF Link</a> | π <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **83.24** | **30.0** | [Demo](http://47.103.63.15:50080/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank"> </a>|
|
| 29 |
+
| WizardMath-70B-V1.0 | π€ <a href="https://huggingface.co/WizardLM/WizardMath-70B-V1.0" target="_blank">HF Link</a> | π <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **81.6** | **22.7** |[Demo](http://47.103.63.15:50083/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a> |
|
| 30 |
+
| WizardMath-13B-V1.0 | π€ <a href="https://huggingface.co/WizardLM/WizardMath-13B-V1.0" target="_blank">HF Link</a> | π <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **63.9** | **14.0** |[Demo](http://47.103.63.15:50082/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a> |
|
| 31 |
+
| WizardMath-7B-V1.0 | π€ <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.0" target="_blank">HF Link</a> | π <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **54.9** | **10.7** | [Demo](http://47.103.63.15:50080/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a>|
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
**Github Repo**: https://github.com/nlpxucan/WizardLM/tree/main/WizardMath
|
| 36 |
+
|
| 37 |
+
**Twitter**: https://twitter.com/WizardLM_AI/status/1689998428200112128
|
| 38 |
+
|
| 39 |
+
**Discord**: https://discord.gg/VZjjHtWrKs
|
| 40 |
+
|
| 41 |
+
## [12/19/2023] Comparing WizardMath-7B-V1.1 with Other 7B size math LLMs.
|
| 42 |
+
|
| 43 |
+
π₯
|
| 44 |
+
β<b>Note for model system prompts usage:</b>
|
| 45 |
+
|
| 46 |
+
Please use **the same systems prompts strictly** with us, and we do not guarantee the accuracy of the **quantified versions**.
|
| 47 |
+
|
| 48 |
+
**Default version:**
|
| 49 |
+
|
| 50 |
+
```
|
| 51 |
+
"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"
|
| 52 |
+
```
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
**CoT Version:** οΌβFor the **simple** math questions, we do NOT recommend to use the CoT prompt.οΌ
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
```
|
| 59 |
+
"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."
|
| 60 |
+
```
|
| 61 |
+
|
| 62 |
+
## Inference WizardMath Demo Script
|
| 63 |
+
|
| 64 |
+
We provide the WizardMath inference demo code [here](https://github.com/nlpxucan/WizardLM/tree/main/demo).
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
## Citation
|
| 70 |
+
|
| 71 |
+
Please cite the repo if you use the data, method or code in this repo.
|
| 72 |
+
|
| 73 |
+
```
|
| 74 |
+
@article{luo2023wizardmath,
|
| 75 |
+
title={WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct},
|
| 76 |
+
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},
|
| 77 |
+
journal={arXiv preprint arXiv:2308.09583},
|
| 78 |
+
year={2023}
|
| 79 |
+
}
|
| 80 |
+
```
|