M

Mimo 7B SFT

Developed by XiaomiMiMo
MiMo-7B-RL is a reinforcement learning model trained based on the MiMo-7B-SFT model, achieving performance comparable to OpenAI o1-mini in mathematical and code reasoning tasks.
Downloads 1,183
Release Time : 4/29/2025

Model Overview

A 7B-parameter language model optimized for reasoning tasks, significantly enhancing mathematical and code reasoning capabilities through reinforcement learning training.

Model Features

Reinforcement Learning Optimization
Significantly improves mathematical and code reasoning capabilities through a carefully designed RL training process.
Multi-token Prediction
Uses MTP technology as an auxiliary training objective, improving both performance and inference speed.
Efficient Inference
The optimized model maintains high performance while achieving faster inference speeds.

Model Capabilities

Mathematical problem solving
Code generation and completion
Logical reasoning
Text understanding and generation
Complex problem solving

Use Cases

Education
Math Problem Solving
Helps students solve various math problems, including advanced math competition questions.
Achieves 68.2% accuracy on AIME math competition problems.
Programming Assistance
Code Generation
Generates executable code based on natural language descriptions.
Achieves 57.8% accuracy on LiveCodeBench tests.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
Š 2025AIbase