Seong Joon Oh's repositories
Otter
🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
qlora
QLoRA: Efficient Finetuning of Quantized LLMs
FastChat
An open platform for training, serving, and evaluating large languages. Release repo for Vicuna and FastChat-T5.
Quantus
Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations
llama
Inference code for LLaMA models
PaLM-rlhf-pytorch
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
helm
Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).
bdl-benchmarks
Bayesian Deep Learning Benchmarks
PfLayer
Learning Features with Parameter-Free Layers, ICLR 2022
pytorch-transformer-ts
Repository of Transformer based PyTorch Time Series Models
YaLM-100B
Pretrained language model with 100B parameters
dash-sample-apps
Open-source demos hosted on Dash Gallery
Efficient-Dataset-Condensation
Official PyTorch implementation of "Dataset Condensation via Efficient Synthetic-Data Parameterization" (ICML'22)
create-react-app-auth-amplify
Implements a basic authentication flow for signing up/signing in users as well as protected client side routing using AWS Amplify.