---
license: llama3.1
base_model:
- meta-llama/Llama-3.1-70B
datasets:
- nvidia/OpenMathInstruct-2
language:
- en
tags:
- nvidia
- math
---

# OpenMath2-Llama3.1-70B-nemo

[NeMo](https://github.com/NVIDIA/NeMo) checkpoint for [OpenMath2-Llama3.1-70B](https://huggingface.co./nvidia/OpenMath2-Llama3.1-70B) which is obtained by finetuning [Llama3.1-70B-Base](https://huggingface.co./meta-llama/Llama-3.1-70B) with [OpenMathInstruct-2](https://huggingface.co./datasets/nvidia/OpenMathInstruct-2).

The model outperforms [Llama3.1-70B-Instruct](https://huggingface.co./meta-llama/Llama-3.1-70B-Instruct) on [MATH](https://github.com/hendrycks/math) by 3.9%. 



| Model | GSM8K | MATH | AMC 2023 | AIME 2024 | Omni-MATH |
|:---|:---:|:---:|:---:|:---:|:---:|
| Llama3.1-8B-Instruct | 84.5 | 51.9 | 9/40 | 2/30 | 12.7 |
| OpenMath2-Llama3.1-8B ([nemo](https://huggingface.co./nvidia/OpenMath2-Llama3.1-8B-nemo) \| [HF](https://huggingface.co./nvidia/OpenMath2-Llama3.1-8B)) | 91.7 | 67.8 | 16/40 | 3/30 | 22.0 |
| + majority@256 | 94.1 | 76.1 | 23/40 | 3/30 | 24.6 |
| Llama3.1-70B-Instruct | 95.8 | 67.9 | 19/40 | 6/30 | 19.0 |
| **OpenMath2-Llama3.1-70B** ([nemo](https://huggingface.co./nvidia/OpenMath2-Llama3.1-70B-nemo) \| [HF](https://huggingface.co./nvidia/OpenMath2-Llama3.1-70B)) | 94.9 | 71.9 | 20/40 | 4/30 | 23.1 |
| + majority@256 | 96.0 | 79.6 | 24/40 | 6/30 | 27.6 |

The pipeline we used to produce the data and models is fully open-sourced!

- [Code](https://github.com/Kipok/NeMo-Skills)
- [Models](https://huggingface.co./collections/nvidia/openmath-2-66fb142317d86400783d2c7b)
- [Dataset](https://huggingface.co./datasets/nvidia/OpenMathInstruct-2)

See our [paper](https://arxiv.org/abs/2410.01560) to learn more details!

# How to use the models?

Our models are trained with the same "chat format" as Llama3.1-instruct models (same system/user/assistant tokens). 
Please note that these models have not been instruction tuned on general data and thus might not provide good answers outside of math domain.

This is a NeMo checkpoint, so you need to use [NeMo Framework](https://github.com/NVIDIA/NeMo) to run inference or finetune it. 
We also release a [HuggingFace checkpoint](https://huggingface.co./nvidia/OpenMath2-Llama3.1-70B) and provide easy instructions on how to
[convert between different formats](https://github.com/Kipok/NeMo-Skills/blob/main/docs/checkpoint-conversion.md) or 
[run inference](https://github.com/Kipok/NeMo-Skills/blob/main/docs/inference.md) with these models using our codebase.

# Reproducing our results

We provide [all instructions](https://github.com/Kipok/NeMo-Skills/blob/main/docs/reproducing-results.md) to fully reproduce our results.

## Citation

If you find our work useful, please consider citing us!

```bibtex
@article{toshniwal2024openmath2,
  title   = {OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data},
  author  = {Shubham Toshniwal and Wei Du and Ivan Moshkov and  Branislav Kisacanin and Alexan Ayrapetyan and Igor Gitman},
  year    = {2024},
  journal = {arXiv preprint arXiv:2410.01560}
}
```

## Terms of use

By accessing this model, you are agreeing to the LLama 3.1 terms and conditions of the [license](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/LICENSE), [acceptable use policy](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/USE_POLICY.md) and [Meta’s privacy policy](https://www.facebook.com/privacy/policy/)