yunyu

langchain

🦜🔗 Build context-aware reasoning applications

ColossalAI

Making large AI models cheaper, faster and more accessible

chatgpt-retrieval-plugin

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

bull

Premium Queue package for handling distributed jobs and messages in NodeJS.

sentence-transformers

Multilingual Sentence & Image Embeddings with BERT

crawlee

Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.

cmdk

Fast, unstyled command menu React component.

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

SwinIR

SwinIR: Image Restoration Using Swin Transformer (official repository)

jsonformer

A Bulletproof Way to Generate Structured JSON from Language Models

FlagAI

FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.

lamini

deepdoctection

A Repo For Document AI

pyserini

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

kernl

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

PTI

Official Implementation for "Pivotal Tuning for Latent-based editing of Real Images" (ACM TOG 2022) https://arxiv.org/abs/2106.05744

sgpt

SGPT: GPT Sentence Embeddings for Semantic Search

parallelformers

Parallelformers: An Efficient Model Parallelization Toolkit for Deployment

info-nce-pytorch

PyTorch implementation of the InfoNCE loss for self-supervised learning.

gpl

Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval" https://arxiv.org/abs/2112.07577

react-nestable

Drag & drop hierarchical list made as a react component

xfspell

xfspell — the Transformer Spell Checker

charformer-pytorch

Implementation of the GBST block from the Charformer paper, in Pytorch

MeGPT

Fine-tune a large language model on your own iMessages

ASP

PyTorch implementation and pre-trained models for ASP - Autoregressive Structured Prediction with Language Models, EMNLP 22. https://arxiv.org/pdf/2210.14698.pdf

synchronicity

Synchronicity lets you interoperate with asynchronous Python APIs.

S3BERT

Semantically Structured Sentence Embeddings

RAFSwap

t2t-tuner

Convenient Text-to-Text Training for Transformers

cppzst

Zstd binding for Nodejs, with TypeScript support.