Openmath CodeLlama 7b Python Hf

Developed by nvidia

The OpenMath model is specifically designed for solving mathematical problems by integrating textual reasoning with Python interpreter-executed code blocks. Trained on the OpenMathInstruct-1 dataset containing 1.8 million math problem-solution pairs.

Large Language Model

Transformers

Supports Multiple Languages#Mathematical reasoning #Python code execution #Instruction fine-tuning

Downloads 83

Release Time : 2/9/2024

Model Overview

This model combines textual reasoning with Python code execution capabilities, focusing on solving mathematical problems, suitable for complex tasks requiring both mathematical computation and programming.

Model Features

Integration of Math and Programming

Combines textual reasoning with Python code execution to effectively solve complex mathematical problems

High-quality Training Data

Trained on the OpenMathInstruct-1 dataset with 1.8 million math problem-solution pairs

Open-source Process

Complete training process and code are open-source, supporting reproduction and improvement

Multiple Scale Options

Offers model versions ranging from 7B to 70B parameters to meet different needs

Model Capabilities

Mathematical problem solving

Python code generation

Mathematical reasoning

Code interpretation and execution

Use Cases

Education

Math Problem Solving

Helps students understand and solve complex mathematical problems

Achieves 75.9% accuracy on the GSM8K dataset

Research

Mathematical Formula Derivation

Assists researchers in deriving and verifying mathematical formulas

Achieves 43.6% accuracy on the MATH dataset

license: llama2 base_model:

codellama/CodeLlama-7b-Python-hf datasets:
nvidia/OpenMathInstruct-1 language:
en tags:
nvidia
code
math

OpenMath-CodeLlama-7b-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!

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

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

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご