---
license: llama3.1
base_model:
- meta-llama/Llama-3.1-8B
datasets:
- nvidia/OpenMathInstruct-2
language:
- en
tags:
- nvidia
- math
---

# OpenMath2-Llama3.1-8B

OpenMath2-Llama3.1-8B is obtained by finetuning [Llama3.1-8B-Base](https://huggingface.co/meta-llama/Llama-3.1-8B) with [OpenMathInstruct-2](https://huggingface.co/datasets/nvidia/OpenMathInstruct-2).

The model outperforms [Llama3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on popular math benchmarks, especially on [MATH](https://github.com/hendrycks/math) by 15.9%. 


| 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)


# How to use the models?

Try to [run inference with our models](https://github.com/Kipok/NeMo-Skills/blob/main/docs/inference.md) with just a few commands!

# Reproducing our results

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

# Improving other models

To improve other models or to learn more about our code, read through the docs below.

- [NeMo-Skills Pipeline](https://github.com/Kipok/NeMo-Skills)
    - [Generating synthetic data](https://github.com/Kipok/NeMo-Skills/blob/main/docs/synthetic-data-generation.md)
    - [Finetuning models](https://github.com/Kipok/NeMo-Skills/blob/main/docs/finetuning.md)
    - [Evaluating models](https://github.com/Kipok/NeMo-Skills/blob/main/docs/evaluation.md)

In our pipeline we use [NVIDIA NeMo](https://www.nvidia.com/en-us/ai-data-science/generative-ai/nemo-framework/),
an end-to-end, cloud-native framework to build, customize, and deploy generative AI models anywhere.
It includes training and inferencing frameworks, guardrailing toolkits, data curation tools, and pretrained models,
offering enterprises an easy, cost-effective, and fast way to adopt generative AI.


## 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}
}
```