RmZeta2718

LLaMA-Factory

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

unsloth

Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

rag-from-scratch

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

flash-attention

Fast and memory-efficient exact attention

gpt-fast

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

modern-unix

A collection of modern/faster/saner alternatives to common unix commands.

DeepSpeedExamples

Example models using DeepSpeed

jq

Command-line JSON processor

pynput

Sends virtual input commands

WebLaTex

A complete alternative for Overleaf with VSCode + Web + Git Integration + Copilot + Grammar & Spell Checker + Live Collaboration Support. Based on GitHub Codespace and Dev container.

SimpleParsing

Simple, Elegant, Typed Argument Parsing with argparse

PDF-Guru

PDF Guru Anki是一款以PDF为中心的多功能办公学习工具箱软件，包含四大板块功能：PDF实用工具箱、Anki制卡神器、Anki最强辅助、视频笔记神器，软件功能众多且强大，熟练运用可以大幅提高办公和学习效率，绝对是您不可多得的效率神器。人生苦短，我用Guru!

ml_timeline

delta

A syntax-highlighting pager for git, diff, grep, and blame output

NTrace-core

NextTrace, an open source visual route tracking CLI tool

annotate-equations

LaTeX package and annotated examples for annotating equations using TikZ.

Finetune_LLAMA

简单易懂的LLaMA微调指南。

viztracer

VizTracer is a low-overhead logging/debugging/profiling tool that can trace and visualize your python code execution.

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

nanoGPT

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

faiss

A library for efficient similarity search and clustering of dense vectors.

Awesome-LLM

Awesome-LLM: a curated list of Large Language Model

pytorch-template

To be the world's best PyTorch project template.

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

stanza

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

spaCy

💫 Industrial-strength Natural Language Processing (NLP) in Python

Chinese-CLIP

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

optuna

A hyperparameter optimization framework

PromptPapers

Must-read papers on prompt-based tuning for pre-trained language models.