hugpadhugpad

baseten / manipulate-matrix-sgd-qwen38_27b-expert

Vision27B660Updated Oct 24, 2026
Hugging Face

Downloads

66

Likes

0

Last updated

Oct 24, 2026

License

apache-2.0

A full-weight reinforcement-learning expert trained by Baseten on Manipulate Matrix using GRPO with SGD. Apply a sequence of specified transformations to a matrix. This release targets the final post-trained inference weights at optimizer update 100, with 6,400 consumed comple…

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