Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

verl: Volcano Engine Reinforcement Learning for LLMs

Open-source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 40+ benchmarks

The simplest, fastest repository for training/finetuning medium-sized GPTs.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Grounded-SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

robomimic: A Modular Framework for Robot Learning from Demonstration

The devkit of the nuScenes dataset.

OpenMMLab Detection Toolbox and Benchmark

MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.

End-to-End Object Detection with Transformers

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

Official implementation of "Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets" (CVPR2021)

Themes for Bootstrap

Contrastive Language-Image Pretraining

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Towards increasing stability of neural networks for continual learning: https://arxiv.org/abs/2006.06958.pdf (NeurIPS'20)

Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in Pytorch

Self-Supervised Learning Toolbox and Benchmark

A PyTorch converter for SimCLR checkpoints

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

TTT Code Release