AIbase
EN
Home
INFRL Qwen2.5 VL 72B Preview Bf16.gguf
I

INFRL Qwen2.5 VL 72B Preview Bf16.gguf

Developed by GeorgyGUF
A vision-language model optimized based on Qwen2.5-VL-72B-Instruct, excelling in multiple visual reasoning benchmarks
Text-to-Image EnglishOpen Source License:Apache-2.0#Visual Reasoning Enhancement#Multimodal Math Problem Solving#Reinforcement Learning Optimization
Downloads 40
Release Time : 5/10/2025

Model Overview

The INFRL-Qwen2.5-VL-72B Preview is a vision-language model optimized from Qwen2.5-VL-72B-Instruct, with enhanced visual reasoning capabilities, achieving outstanding performance in benchmarks such as MathVision, MathVista, and MathVerse.

Model Features

Enhanced Visual Reasoning
Specially optimized visual reasoning capabilities based on Qwen2.5-VL-72B-Instruct
Leading in Multiple Benchmarks
Top performance in multiple visual reasoning benchmarks including MathVision, MathVista, and MathVerse
Open-Source Model
As an open-source vision-language model, it outperforms commercial models in various tests

Model Capabilities

Visual Question Answering
Image Understanding
Mathematical Reasoning
Multimodal Understanding

Use Cases

Education
Math Problem Solving
Solving math problems containing diagrams and formulas
Achieved 41.9 points on the MathVision test set
Research
Visual Reasoning Research
Used for evaluating and researching vision-language model capabilities
Achieved 77.8 points on the MathVista test mini-set
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase