Zhijian's repositories
vit-pytorch
vit model from tensorflow
BiSeNet
Add bisenetv2. My implementation of BiSeNet
botty
D2R Pixel Bot
dino
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
GolangLeetcode
AC leetcode with goLang
ImageNet21K
Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(2021) paper
JGM-Automator
《家国梦》游戏自动化脚本。
Langchain-Chatchat
Langchain-Chatchat(原Langchain-ChatGLM)基于 Langchain 与 ChatGLM 等语言模型的本地知识库问答 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain
lightweight-neural-architecture-search
This is a collection of our zero-cost NAS and efficient vision applications.
LLaMA-Factory
Unify Efficient Fine-Tuning of 100+ LLMs
LM-playground
repo contains mutil LLM & VL demo
once-for-all
[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment
OpenDiT
OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and Inference
Pai-Megatron-Patch
The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.
ProxylessNAS
[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware.
pytracking
Visual tracking library based on PyTorch.
scenic
Scenic: A Jax Library for Computer Vision Research and Beyond
slimmable_networks
Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019
SparseR-CNN
End-to-End Object Detection with Learnable Proposal
Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Swin-Transformer-Object-Detection
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.
TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.