TakeruEndo

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.

langchain

🦜🔗 Build context-aware reasoning applications

open-interpreter

A natural language interface for computers

MetaGPT

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

TaskMatrix

tuning_playbook

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

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

JARVIS

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

babyagi

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

guidance

A guidance language for controlling large language models.

alpaca-lora

Instruct-tune LLaMA on consumer hardware

CVPR2024-Papers-with-Code

CVPR 2024 论文和开源项目合集

Grounded-Segment-Anything

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

petals

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

ImageBind

ImageBind One Embedding Space to Bind Them All

mergekit

Tools for merging pretrained large language models.

Flux.jl

Relax! Flux is the ML library that doesn't make you tensor

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

lightning-hydra-template

PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡

opendal

Apache OpenDAL: access data freely.

mujoco-py

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

notion-qa

Caption-Anything

Caption-Anything is a versatile tool combining image segmentation, visual captioning, and ChatGPT, generating tailored captions with diverse controls for user preferences. https://huggingface.co/spaces/TencentARC/Caption-Anything https://huggingface.co/spaces/VIPLab/Caption-Anything

vscode-dbt-power-user

This extension makes vscode seamlessly work with dbt™: Auto-complete, preview, column lineage, AI docs generation, health checks, cost estimation etc

Ascender

Accelerator of Scientific Development and Research. A project template developed by XCCV group of cvpaper.challenge.

HandyRL

HandyRL is a handy and simple framework based on Python and PyTorch for distributed reinforcement learning that is applicable to your own environments.

toolformer-zero

React app implementing OpenAI and Google APIs to re-create behavior of the toolformer paper.

GPTSAN

General-purpose Swich transformer based Japanese language model