W

Westseverus 7B DPO V2

Developed by PetroGPT
WestSeverus-7B-DPO-v2 is a WestLake family model trained based on WestSeverus-7B, with training on multiple DPO datasets, demonstrating excellent performance in basic mathematical problems.
Downloads 437
Release Time : 1/24/2024

Model Overview

This model can be applied in fields such as mathematics, chemistry, physics, and even programming for further research and reference.

Model Features

Outstanding Mathematical Ability
Excels in basic mathematical problems, suitable for fields like mathematics, chemistry, and physics.
Multidisciplinary Applications
Applicable in fields such as mathematics, chemistry, physics, and even programming.
DPO Training
Trained on multiple DPO datasets, enhancing model performance.

Model Capabilities

Text generation
Q&A systems
Mathematical problem solving
Programming assistance

Use Cases

Education
Mathematical Problem Solving
Helps students solve basic mathematical problems
Achieved a score of 71.65 on the GSM8K mathematical benchmark.
Research
Scientific Problem Research
Assists researchers in studying problems in fields like chemistry and physics
Programming
Code Generation
Assists programmers in generating code snippets
Achieved a score of 43.3 on the HumanEval benchmark.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase