OpenMath-CodeLlama-34b-Python-hf

OpenMath models were designed to solve mathematical problems by integrating text-based reasoning with code blocks executed by Python interpreter. The models were trained on OpenMathInstruct-1, a math instruction tuning dataset with 1.8M problem-solution pairs generated using permissively licensed Mixtral-8x7B model.

	greedy		majority@50
model	GSM8K	MATH	GMS8K	MATH
OpenMath-CodeLlama-7B (nemo | HF)	75.9	43.6	84.8	55.6
OpenMath-Mistral-7B (nemo | HF)	80.2	44.5	86.9	57.2
OpenMath-CodeLlama-13B (nemo | HF)	78.8	45.5	86.8	57.6
OpenMath-CodeLlama-34B (nemo | HF)	80.7	48.3	88.0	60.2
OpenMath-Llama2-70B (nemo | HF)	84.7	46.3	90.1	58.3
OpenMath-CodeLlama-70B (nemo | HF)	84.6	50.7	90.8	60.4

The pipeline we used to produce these models is fully open-sourced!

• Code
• Models
• Dataset

See our paper for more details!

How to use the models?

Try to run inference with our models with just a few commands!

Reproducing our results

We provide all instructions 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
  • Generating synthetic data
  • Finetuning models
  • Evaluating models

In our pipeline we use NVIDIA NeMo, 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!

@article{toshniwal2024openmath,
  title   = {OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset},
  author  = {Shubham Toshniwal and Ivan Moshkov and Sean Narenthiran and Daria Gitman and Fei Jia and Igor Gitman},
  year    = {2024},
  journal = {arXiv preprint arXiv: Arxiv-2402.10176}
}

License

The use of this model is governed by the Llama 2 Community License Agreement