Explore live open-source projects and AI models.

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

A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

• OpenTrit, an open-source cross-framework mixed ternary toolkit, supports one-click conversion of mixed ternary models between PyTorch and TensorFlow. It encapsulates heterogeneous computing power scheduling and quantization optimization, addressing the issues of "framework dependency and poor u... Read more

using Neural Networks (SSD) on Tensorflow. This repo documents steps and scripts used to train a hand detector using Tensorflow (Object Detection API). As with any DNN based task, the most expensive (and riskiest) part of the process has to do with finding or creating the right (annotated) datas... Read more

Model Pruning and Quantization using Tensorflow

Guide for quantization, conversation of the tensorflow model to tensorflow lite

AWD-LSTM from "Regularizing and Optimizing LSTM Language Models" with training-award quantization support for tensorflow.

A tutorial of model quantization using TensorFlow