Stars
Entropy Based Sampling and Parallel CoT Decoding
SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.
Machine Learning Engineering Open Book
A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)
Example models using DeepSpeed
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
A compendium of informations regarding Stable Diffusion (SD)
Dataset of prompts, synthetic AI generated images, and aesthetic ratings.
"Understanding Dataset Difficulty with V-Usable Information" (ICML 2022, outstanding paper)
Stanford LaTeX poster template
Code for Blodgett et al. 2016, Demographic dialectal variation in social media
Repository for the paper "Automated Hate Speech Detection and the Problem of Offensive Language", ICWSM 2017
Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models
An application that allows you to design and test your own stock trading algorithms in an attempt to beat the market.
The goal of this project is to enable users to create cool web demos using the newly released OpenAI GPT-3 API with just a few lines of Python.
Official Github repo for the paper "Unifying Human and Statistical Evaluation for Natural Language Generation"
State-of-the-Art Text Embeddings
Collection of notebooks about quantitative finance, with interactive python code.
Understanding ML and deep learning through geometry
Code for papers "A Surprisingly Robust Trick for Winograd Schema Challenge" and "WikiCREM: A Large Unsupervised Corpus for Coreference Resolution"
higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.
Course repo for Applied Natural Language Processing (Spring 2019)
Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts
🦄 State-of-the-Art Conversational AI with Transfer Learning
Semantic Textual Similarity in Python