SakanaAI / RLT-7B

Text Generation7.6B11119Updated Jun 22, 2025

Downloads

111

Likes

19

Last updated

Jun 22, 2025

License

apache-2.0

This repository contains a 7B parameter student model trained using the Reinforcement-Learned Teachers (RLT) pipeline introduced in our paper Reinforcement Learning Teachers.

Tasks & library

  • text generation

Tags

  • qwen2
  • reasoning
  • reinforcement
  • learning
  • RLT
  • math

Technical specifications

Parameters7.6B
LibraryNot available
Languagesen, zh
Licenseapache-2.0