QLoRA: Efficient Finetuning of Quantized LLMs

Universal LLM Deployment Engine with ML Compilation

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

Cramming the training of a (BERT-type) language model into limited compute.

PyTorch code for the CVPR'23 paper: "CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning"

Stable Diffusion web UI

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, an…

Powerful CLI tool to simplify Amazon ECS deployments, rollbacks & scaling

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep lear…

This repository contains small projects related to Neural Networks and Deep Learning in general. Subjects are closely linekd with articles I publish on Medium. I encourage you both to read as well …

Essential Cheat Sheets for deep learning and machine learning researchers https://medium.com/@kailashahirwar/essential-cheat-sheets-for-machine-learning-and-deep-learning-researchers-efb6a8ebd2e5

Annotator for Chinese Text Corpus (UNDER DEVELOPMENT) 中文文本标注工具

This sample show you how to train BERT on Amazon Sagemaker using Spot instances

Modular search for Django

爬虫案例合集。包括但不限于《淘宝、京东、天猫、豆瓣、抖音、快手、微博、微信、阿里、头条、pdd、优酷、爱奇艺、携程、12306、58、搜狐、各种指数、维普万方、Zlibraty、Oalib、小说、招标网、采购网、小红书、大众点评、推特、脉脉、知乎》

整理知识图谱相关学习资料

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

AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data…

This is the code for my WWW2015 paper

A topic-centric list of HQ open datasets.

😎 Awesome lists about all kinds of interesting topics

semantic similarity framework for knowledge graph

chinesetokenization