Hongyu Wang's repositories
awesome-detection-transformer
Collect some papers about transformer for detection and segmentation. Awesome Detection Transformer for Computer Vision (CV)
deep-learning-for-image-processing
deep learning for image processing including classification and object-detection etc.
detr
End-to-End Object Detection with Transformers
detrex
detrex is a research platform for Transformer-based Instance Recognition algorithms including DETR (ECCV 2020), Deformable-DETR (ICLR 2021), Conditional-DETR (ICCV 2021), DAB-DETR (ICLR 2022), DN-DETR (CVPR 2022), DINO (ICLR 2023), H-DETR (CVPR 2023), MaskDINO (CVPR 2023), etc.
fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
flash-attention
Fast and memory-efficient exact attention
gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
LAVIS
LAVIS - A One-stop Library for Language-Vision Intelligence
mae
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
MT-Reading-List
A machine translation reading list maintained by Tsinghua Natural Language Processing Group
torchscale
Transformers at any scale
JARVIS
JARVIS, a system to connect LLMs with ML community
LMOps
General technology for enabling AI capabilities w/ LLMs and MLLMs
Metaworld
Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning
OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)
openvla
OpenVLA: An open-source vision-language-action model for robotic manipulation.
TransformerEngine
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
ustcwhy.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
VideoMAE
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
VILA
VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)