Search Packages

neural-compressor

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

suod

(MLSys' 21) An Acceleration System for Large-scare Unsupervised Heterogeneous Outlier Detection (Anomaly Detection)

paddleclas

A treasure chest for visual classification and recognition powered by PaddlePaddle

resonance-layer

Emotional intelligence layer for AI - detects emotion, tracks wellbeing, and gives any LLM the context to respond to how people actually feel.

langformers

🚀 Unified NLP Pipelines for Language Models

torchdistill

A coding-free framework built on PyTorch for reproducible deep learning studies. PyTorch Ecosystem. 🏆26 knowledge distillation methods presented at TPAMI, CVPR, ICLR, ECCV, NeurIPS, ICCV, AAAI, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.

neural-compressor-pt

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

ssondo

Official SSONDO implementation and trained model's weights (ICASSP 2026)

uni-layer

30+ layer contribution metrics from 7 theoretical categories for PyTorch model compression. Bridges for Torch-Pruning and PEFT/LoRA.

mmrazor

OpenMMLab Model Compression Toolbox and Benchmark.

neural-compressor-tf

Repository of Intel® Neural Compressor

aquvitae

The easiest Knowledge Distillation library for Light Weight DeepLearning

ollama-rag

A programming framework for knowledge management

neural-compressor-full

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

easy-zh-bert

easy-bert是一个中文NLP工具，提供诸多bert变体调用和调参方法，极速上手；清晰的设计和代码注释，也很适合学习

kd-lib

A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.

insurance-distill

GBM-to-GLM distillation for insurance pricing - surrogate factor tables for Radar/Emblem rating engines

neural-solution

Repository of Intel® Neural Compressor

lpot

Repository of Intel® Low Precision Optimization Tool

neural-insights

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

sc2bench

[TMLR] "SC2 Benchmark: Supervised Compression for Split Computing"

easytransfer

EasyTransfer is designed to make the development of transfer learning in NLP applications easier.

zhijian

ZhiJian: A Unifying and Rapidly Deployable Toolbox for Pre-trained Model Reuse

ilit

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime