Stars
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
A comprehensive template for aligning large language models (LLMs) using Reinforcement Learning from Human Feedback (RLHF), transfer learning, and more. Build your own customizable LLM alignment so…
The QueryNER dataset, developed by Brandeis University and eBay.
Python APIs for web automation, testing, and bypassing bot-detection.
Delving into the Realm of LLM Security: An Exploration of Offensive and Defensive Tools, Unveiling Their Present Capabilities.
Awesome Search - this is all about the (e-commerce, but not only) search and its awesomeness
A brand tagging system in product titles and user generated text
Corpus of domain names scraped from Common Crawl and manually annotated to add word boundaries (e.g. "commoncrawl" to "common crawl").
🧠 A study guide to learn about Transformers
Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".
21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/
🧠💬 Articles I wrote about machine learning, archived from MachineCurve.com.
The project page for "LOGIC-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning"
LLM Workshop by Sourab Mangrulkar
Sparse and discrete interpretability tool for neural networks
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Robust recipes to align language models with human and AI preferences
Friends don't let friends make certain types of data visualization - What are they and why are they bad.
A list of awesome resources for Computational Social Science
Convert PDF to markdown + JSON quickly with high accuracy
Controlled Text Generation via Language Model Arithmetic
A collection of over 120'000 Telegram Channels
ImageBind One Embedding Space to Bind Them All
Advanced python library to scrap Twitter (tweets, users) from unofficial API
The library that uses dependency parsing to preprocess text to train DisSent model
Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"