liyier90's repositories
FairMOT-cpp
An inference-only C++ implementation of FairMOT.
pytorch-dcnv2
PyTorch Deformable Convolutional Networks v2 (no compile required)
composer
Train neural networks up to 7x faster
cpplint
Static code checker for C++
cython_bbox
standalone cython_bbox borrowed from faster-rcnn
DCNv2
Deformable Convolutional Networks v2 with Pytorch
exllamav2
A fast inference library for running LLMs locally on modern consumer-class GPUs
FairMOT
[IJCV-2021] FairMOT: On the Fairness of Detection and Re-Identification in Multi-Object Tracking
FastMOT
High-performance multiple object tracking based on YOLO, Deep SORT, and KLT 🚀
GitHub-Dark
:octocat: Dark GitHub style
llama.cpp
Port of Facebook's LLaMA model in C/C++
liyier90.conda
Manage conda environment and packages with Ansible
llama
Inference code for LLaMA models
llm-foundry
LLM training code for MosaicML foundation models
Megatron-LM
Ongoing research training transformer models at scale
PeekingDuck
A modular framework built to simplify Computer Vision inference workloads.
pkd-custom-projects
A collection of PeekingDuck projects using custom nodes
SeaEval
NAACL 2024: SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning
TinyLlama
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
Towards-Realtime-MOT
Joint Detection and Embedding for fast multi-object tracking
Towards-Realtime-MOT-Cpp
A C++ codebase implementation of Towards-Realtime-MOT
Unfit
Data fitting and optimization software
vscode-yaml
YAML support for VS Code with built-in kubernetes syntax support
yaml-language-server
Language Server for YAML Files
yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
YOLOv6
YOLOv6: a single-stage object detection framework dedicated to industrial applications.
YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/