中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3

中华人民共和国密码行业标准(GM/T)文本

A high-throughput and memory-efficient inference and serving engine for LLMs

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

An open source, portable, easy to use, readable and flexible TLS library, and reference implementation of the PSA Cryptography API. Releases are on a varying cadence, typically around 3 - 6 months …

中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

LLM inference in C/C++

Model library for live2d-widget.js

The Security Toolkit for LLM Interactions

记录个人的学习历程。包括但不限于算法、机器学习、论文写作等。

The one and only one gfwlist here

Trust Domain Extensions (TDX) is introducing new, architectural elements to help deploy hardware-isolated, virtual machines (VMs) called trust domains (TDs). Intel TDX is designed to isolate VMs fr…

Keras Datasets 国内下载镜像

Zhouyi model zoo (Maintained at https://github.com/Arm-China/Model_zoo)

Models and examples built with TensorFlow

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.

StableLM: Stability AI Language Models

Making large AI models cheaper, faster and more accessible

cudnn_frontend provides a c++ wrapper for the cudnn backend API and samples on how to use it

z - jump around

🚀 A modern-looking Code Editor

A curated list of open-source projects that help exploit Intel SGX technology

GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI思想)

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Examples for HIP

Several simple examples for popular neural network toolkits calling custom CUDA operators.

Learn the technology of CUDA and GPU Programming. The main is learn from the book of "CUDA Programming: A Developer's Guide to Parallel Computing with GPUS"

This is an attempt to implement Spectre on ARMv7