AIPython★ 411⑂ 14 forks
OpenMOSS/EasyWAM
World Action Model Toolkit
Provides a unified Python framework for training, fine-tuning, and evaluating World Action Models (WAMs) with modular components and standard APIs.
// KEY FEATURES
- Train WAMs from scratch using configurable datasets and loss functions.
- Fine‑tune pretrained World Action Models with few‑shot adaptation scripts.
- Evaluate models via standardized benchmarks and generate detailed performance reports.
#benchmark#codebase#embodied-ai#foundation-models#lora#robotics#vision-language-action#world-action-model#world-models
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram