Sun Haozhe's starred repositories
VisionLLaMA
VisionLLaMA: A Unified LLaMA Interface for Vision Tasks
leetcode_company_wise_questions
This is a repository containing the list of company wise questions available on leetcode premium
Mistral-DNA
Large language model Mistral for DNA
llm-action
本项目旨在分享大模型相关技术原理以及实战经验。
bbb-recording-exporter
A client- and server side script to generate BigBlueButton MP4 recordings.
bbb-video-download
A BigBlueButton recording postscript to provide video download
Efficient-Deep-Learning
Collection of recent methods on (deep) neural network compression and acceleration.
LLM-Pruner
[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support LLaMA, Llama-2, BLOOM, Vicuna, Baichuan, etc.
Torch-Pruning
[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs
Pdf-Presenter-Console
A Keynote like presenter console with multi-monitor support and the ability to read PDF as input files.
zero-cost-nas
Zero-Cost Proxies for Lightweight NAS
neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
accelerate
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
imagenette
A smaller subset of 10 easily classified classes from Imagenet, and a little more French
CausalDiscoveryToolbox
Package for causal inference in graphs and in the pairwise settings. Tools for graph structure recovery and dependencies are included.
musco-pytorch
MUSCO: MUlti-Stage COmpression of neural networks
torchsparse
[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.
spconv_lite
sparse convolution lib. derived from spconv
SparseConvNet
CNN - Derived from https://github.com/btgraham/SparseConvNet, modified for max os.