Stars
Codebase for "On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback". This repo implements a generative multi-turn RL environment with support for agent, user, user feedback…
The simplest, fastest repository for training/finetuning medium-sized GPTs.
BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).
Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
Investigating using first vs third person feedback for reward modeling
Library for graphical models of decision making, based on pgmpy and networkx
15.003 Analytics Tools - Course Materials
Data on COVID-19 (coronavirus) cases, deaths, hospitalizations, tests • All countries • Updated daily by Our World in Data
DELPHI: The Epidemiological model underlying COVIDAnalytics
This repository offers an implementation of some common architectures for normalizing flows.
Implementation of Unconstrained Monotonic Neural Network and the related experiments. These architectures are particularly useful for modelling monotonic transformations in normalizing flows.
Transparent calculations with uncertainties on the quantities involved (aka "error propagation"); calculation of derivatives.
Contains Pokerbots course resources for IAP 2021
Graphical analysis of structural causal models / graphical causal models.
Probabilistic reasoning and statistical analysis in TensorFlow
A modular framework for neural networks with Euclidean symmetry
Moment Decorrelation for constrained NN outputs with respect to protected attributes. (Decorrelated (flat), linear, quadratic, etc.)
Codebase for the Summary Loop paper at ACL2020
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
machine learning with logical rules in Python
Keras/Pytorch implementation of N-BEATS: Neural basis expansion analysis for interpretable time series forecasting.