huntzhan

hoppscotch

Open source API development ecosystem - https://hoppscotch.io (open-source alternative to Postman, Insomnia)

Awesome-LLM

Awesome-LLM: a curated list of Large Language Model

awesome-system-design-resources

Learn System Design concepts and prepare for interviews using free resources.

ChatGLM3

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

triton

Development repository for the Triton language and compiler

MemGPT

Create LLM agents with long-term memory and custom tools 📚🦙

ggml

Tensor library for machine learning

Megatron-LM

Ongoing research training transformer models at scale

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

Yi

A series of large language models trained from scratch by developers @01-ai

llama-cpp-python

Python bindings for llama.cpp

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

next-terminal

Next Terminal是一个简单好用安全的开源交互审计系统，支持RDP、SSH、VNC、Telnet、Kubernetes协议。

alignment-handbook

Robust recipes to align language models with human and AI preferences

grobid

A machine learning software for extracting information from scholarly documents

chatglm.cpp

C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4

LLM-Agent-Survey

RecommenderSystem

ctransformers

Python bindings for the Transformer models implemented in C/C++ using GGML library.

FinGLM

FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目，利用开源开放来促进「AI+金融」。

SGK_Sites_and_Bots

免费在线社工库，免费Telegram社工库

Skywork

Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc. 天工系列模型在3.2TB高质量多语言和代码数据上进行预训练。我们开源了模型参数，训练数据，评估数据，评估方法。

AI-interview-cards

最完整的AI算法面试题目仓库，1000道，25个类目

linux-timemachine

Rsync-based OSX-like time machine for Linux, MacOS and BSD for atomic and resumable local and remote backups

Index-1.9B

A SOTA lightweight multilingual LLM

GPU-Benchmarks-on-LLM-Inference

Multiple NVIDIA GPUs or Apple Silicon for Large Language Model Inference?

float8_experimental

This repository contains the experimental PyTorch native float8 training UX

COIG-CQIA