Contrastive Language-Image Pretraining

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

A crude RLHF layer on top of nanoGPT with Gumbel-Softmax trick

Learn how to design Machine Learning systems and prepare for an interview.

Easily compute clip embeddings and build a clip retrieval system with them

PyTorch image models, scripts, pretrained weights -- (SE)ResNet/ResNeXT, DPN, EfficientNet, MixNet, MobileNet-V3/V2, MNASNet, Single-Path NAS, FBNet, and more

Readings for Analytics Engineers