hugpadhugpad

baseten / rush-hour-adam-qwen38_27b-expert

Vision27B820Updated Oct 26, 2026
Hugging Face

Downloads

82

Likes

0

Last updated

Oct 26, 2026

License

apache-2.0

A full-weight reinforcement-learning expert trained by Baseten on Rush Hour using GRPO with Adam. Solve the Rush Hour sliding-block puzzle. This repository contains the final inference checkpoint after 100 optimizer updates.

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • qwen3_5
  • image-text-to-text
  • reasoning-gym
  • reinforcement-learning
  • grpo

Technical specifications

Parameters27B
Librarytransformers
Languagesen
Base modelQwen/Qwen3.8-27B
Licenseapache-2.0