dblate

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

DeepSpeed

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

dify

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

stanford_alpaca

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

autogen

A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap

LLaMA-Factory

Unify Efficient Fine-Tuning of 100+ LLMs

vllm

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

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Qwen

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

DALLE2-pytorch

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

tokenizers

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

LWM

corenet

CoreNet: A library for training deep neural networks

interpy-zh

📘《Python进阶》（Intermediate Python - Chinese Version）

lm-evaluation-harness

A framework for few-shot evaluation of language models.

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

intermediatePython

leptonai

A Pythonic framework to simplify AI service building

webdataset

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

course

The Hugging Face course on Transformers

datatrove

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

ceval

Official github repo for C-Eval, a Chinese evaluation suite for foundation models [NeurIPS 2023]

vae

a simple vae and cvae from keras

cc_net

Tools to download and cleanup Common Crawl data

CMMLU

CMMLU: Measuring massive multitask language understanding in Chinese

bagel

A bagel, with everything.

MMMU

This repo contains evaluation code for the paper "MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI"

doremi

Pytorch implementation of DoReMi, a method for optimizing the data mixture weights in language modeling datasets

NeMo-Skills

A pipeline to improve skills of large language models