chiennv2000

shell_gpt

A command-line productivity tool powered by AI large language models like GPT-4, will help you accomplish your tasks faster and more efficiently.

readme-md-generator

📄 CLI that generates beautiful README.md files

AutoGPTQ

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

nanotron

Minimalistic large language model 3D-parallelism training

mergekit

Tools for merging pretrained large language models.

llm-autoeval

Automatically evaluate your LLMs in Google Colab

VMLU

LLaMA-Pro

[ACL 2024] Progressive LLaMA with Block Expansion.

axolotl

Go ahead and axolotl questions

parallelformers

Parallelformers: An Efficient Model Parallelization Toolkit for Deployment

Megatron-LLM

distributed trainer for LLMs

ml-engineering

Machine Learning Engineering Open Book

xTuring

Build, customize and control you own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6

PointTransformerV3

[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)

funsearch

weak-to-strong

datablations

Scaling Data-Constrained Language Models

TinyLlama

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

vllm

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

project-based-learning

Curated list of project-based tutorials

GPTs

leaked prompts of GPTs

Pearl

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

megablocks-public

mlx

MLX: An array framework for Apple silicon

On-Demand-IE

Code and dataset for the emnlp paper titled Instruct and Extract: Instruction Tuning for On-Demand Information Extraction

causal-conv1d

Causal depthwise conv1d in CUDA, with a PyTorch interface

mamba

meditron

Meditron is a suite of open-source medical Large Language Models (LLMs).