Zijian Hu's starred repositories
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
paper-reading
深度学习经典、新论文逐段精读
autocomplete
IDE-style autocomplete for your existing terminal & shell
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
JetBrainsMono
JetBrains Mono – the free and open-source typeface for developers
LLMsPracticalGuide
A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)
mmtracking
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
pytorchvideo
A deep learning library for video understanding research.
Awesome-Video-Diffusion
A curated list of recent diffusion models for video generation, editing, restoration, understanding, etc.
awesome-semi-supervised-learning
😎 An up-to-date & curated list of awesome semi-supervised learning papers, methods & resources.
Awesome-Video-Datasets
Video datasets
llm-engine
Scale LLM Engine public repository
Megatron-LLM
distributed trainer for LLMs
pytorch_ema
Tiny PyTorch library for maintaining a moving average of a collection of parameters.
pillow_heif
Python library for working with HEIF images and plugin for Pillow.
conda-bash-completion
Bash completion support for conda
distributed-pytorch
Distributed, mixed-precision training with PyTorch