Utilities intended for use with Llama models.

Official release of InternLM2.5 7B base and chat models. 1M context support

LLM101n: Let's build a Storyteller

A library for advanced large language model reasoning

A utility to list and activate Azure Entra ID Privileged Identity Management roles from the CLI

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

MSCCL++: A GPU-driven communication stack for scalable AI applications

Lib acoustic sensing is a utility library easing the process to design apps based on acoustic information

A Simulation Environment to train Robots in Large Realistic Interactive Scenes

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Prov-GigaPath: A whole-slide foundation model for digital pathology from real-world data

MSVBASE is a system that efficiently supports complex queries of both approximate similarity search and relational operators. It integrates high-dimensional vector indices into PostgreSQL, a relati…

This folder provides the neural-based LoRa demodulation code for our ICLR 2023 workshop paper: NELORA-BENCH: A BENCHMARK FOR NEURAL ENHANCED LORA DEMODULATION

Denoising Diffusion Probabilistic Models

NeuroKit2: The Python Toolbox for Neurophysiological Signal Processing

A package for processing signals recorded using wearable sensors, such as Electrocardiogram (ECG), Photoplethysmogram (PPG), Electrodermal activity (EDA) and 3-axis acceleration (ACC).

A library for extracting a wide range of features from single-lead ECG waveforms.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

An open-source, high-performance SQL vector database built on ClickHouse.

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

《剑指 Offer》 Python, Java, C++ 解题代码，LeetBook《图解算法数据结构》配套代码仓

《Hello 算法》：动画图解、一键运行的数据结构与算法教程。支持 Python, Java, C++, C, C#, JS, Go, Swift, Rust, Ruby, Kotlin, TS, Dart 代码。简体版和繁体版同步更新，English version ongoing

无线与深度学习结合的论文代码整理/Paper-with-Code-of-Wireless-communication-Based-on-DL

This is a landscape of the infrastructure that powers the generative AI ecosystem

A universal time series representation learning framework

LlamaIndex is a data framework for your LLM applications

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

An offical implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers."

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722