Skip to main content
Back to HUD Frontier / RSI RL Environments Hackathon Gallery

Project spotlight

Approved

Env0

Data recipe, training recipe, evals for on device models on mobile on generalist tasks

Env0

About This Project

  • trained model weights
  • sft / rl pipeline
  • data recipe: sft traces, rl environments
    • multimodal,
  • an eval set for agents with on device llms powering mobile use cases

Repository

Python81.6%Shell11.1%Dockerfile3.4%HTML3%Swift0.8%JavaScript0.1%
AGPL-3.0Last commit 3 months ago