W

Wizardmath 7B V1.1

Developed by WizardLMTeam
WizardMath-7B-V1.1 is a state-of-the-art 7B mathematical large language model trained on Mistral-7B, excelling on GSM8k and MATH datasets.
Downloads 175.35k
Release Time : 12/19/2023

Model Overview

WizardMath empowers large language models with mathematical reasoning capabilities through Reinforced Evolutionary Instructions (RLEIF), focusing on solving mathematical problems.

Model Features

Reinforced Evolutionary Instructions
Enhances the model's mathematical reasoning through the RLEIF method.
High Performance
Achieves state-of-the-art performance on GSM8k and MATH datasets.
Open Source
The model and code are publicly available for research and application.

Model Capabilities

Mathematical Problem Solving
Mathematical Reasoning
Text Generation

Use Cases

Education
Mathematical Problem Solving
Assists students in solving complex mathematical problems.
Achieves 83.2 pass@1 on GSM8k.
Research
Mathematical Reasoning Research
Used to study the mathematical reasoning capabilities of large language models.
Achieves 33.0 pass@1 on MATH.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase