suiyan538 Goto Github PK

aisystem

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

annotated_deep_learning_paper_implementations

🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

auto-gpt

An experimental open-source attempt to make GPT-4 fully autonomous.

awesome-chinese-llm

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

awesome-llm

Awesome-LLM: a curated list of Large Language Model

came

The official implementation of "CAME: Confidence-guided Adaptive Memory Optimization"

colossalai

Making large AI models cheaper, faster and more accessible

deepspeed

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

deepspeedexamples

Example models using DeepSpeed

efficient-kan

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

flash-attention

Fast and memory-efficient exact attention

flashattention-pytorch

Implementation of FlashAttention in PyTorch

gpt-2-output-dataset

Dataset of GPT-2 outputs for research in detection, biases, and more

gpt-3

GPT-3: Language Models are Few-Shot Learners

gpt-neox-origin-

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

gpt3-pytorch

Unofficial PyTorch Implementation of OpenAI's GPT-3

gpt4free

decentralising the Ai Industry, just some language model api's...

llama

Inference code for LLaMA models

llm-action

本项目旨在分享大模型相关技术原理以及实战经验。

llms_interview_notes

LLMs interview notes and answers:该仓库主要记录大模型（LLMs）算法工程师相关的面试题和参考答案

loramoe

LoRAMoE: Revolutionizing Mixture of Experts for Maintaining World Knowledge in Language Model Alignment

merak

moslora

pretrained-language-model

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

pykan

Kolmogorov Arnold Networks

the-algorithm

Source code for Twitter's Recommendation Algorithm

torchscale

Foundation Architecture for (M)LLMs

triton

Development repository for the Triton language and compiler

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

zero-bubble-pipeline-parallelism

Zero Bubble Pipeline Parallelism