Leo Gao's repositories
toy-alignment-notebooks
The goal of this project is to collect beginner friendly notebooks for demonstrating alignment concepts in toy environments and make them feel more tangible.
gpt2-hf-to-tf1
Convert TF 2.x/Pytorch GPT2 model to original OpenAI TF 1.x GPT2 format
akronomicon
Public rankings of extreme-scale models
alignment-research-dataset
A dataset of alignment research and code to reproduce it
CLIP
Contrastive Language-Image Pretraining
dask
Parallel computing with task scheduling
GPT-Neo-visual-grounding
Visually ground GPT-Neo 1.3b and 2.7b
learn2gradienthack
Uses learn2learn to train a fully connected network that implements the constant function and resists SGD
mesh-transformer-jax
Model parallel transformers in JAX and Haiku
publish_perish
Academia sim
ray
An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
scaling-experiments
Experiments related to scaling laws for language models.
tensor2tensor
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
The-Pile-FreeLaw
Download, parse, and filter data from Court Listener, part of the FreeLaw projects. Data-ready for The-Pile.
transformers
🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.