26m function call model that runs on incredibly small devices
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
A collection of high-quality models for the MuJoCo physics engine
Generates original ARC-AGI-1-style tasks distribution-matched
High-resolution models for human tasks
A Conversational Speech Generation Model
Tooling for the Common Objects In 3D dataset
Learning to Act by Watching Unlabeled Online Videos
PyTorch implementation of YOLOv4
An implementation of model parallel GPT-2 and GPT-3-style models
Reproduces results of "Fixing the train-test resolution discrepancy"
Environment generation code for the paper "Emergent Tool Use"