lxuechen

A codebase that makes differentially private training of transformers easy.

PyTorch implementation of Bidirectional Monte Carlo, Annealed Importance Sampling, and Hamiltonian Monte Carlo.

An ML research codebase built with friends :)

Code for "Inference Suboptimality in Variational Autoencoders"

Code for ICLR 2022 submission "Differentially Private Fine-tuning of Language Models".

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

What would you do with 1000 H100s...

Code for "Latent ODEs for Irregularly-Sampled Time Series" paper

Model interpretability and understanding for PyTorch

Training PyTorch models with differential privacy

Legibile, Scalable, Reproducible Foundation Models with Named Tensors and Jax

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Algorithms for Privacy-Preserving Machine Learning in JAX

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

8-bit CUDA functions for PyTorch

No description.

Development repository for the Triton language and compiler

Configs and boilerplates for Label Studio's Machine Learning backend

VSCode extension that allows you to use GPT3 inside the IDE

my thesis

A high-throughput and memory-efficient inference and serving engine for LLMs

A list of AI autonomous agents

Master programming by recreating your favorite technologies from scratch.

The website designer for Hugo. Build and deploy a beautiful website in minutes :rocket:

Fast and memory-efficient exact attention

Automatically split your PyTorch models on multiple GPUs for training & inference

Ongoing research training transformer models at scale

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

No description.

An open-source framework for training large multimodal models.

No description.

No description.

A game theoretic approach to explain the output of any machine learning model.

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

No description.

Aligning pretrained language models with instruction data generated by themselves.

A minimal PyTorch re-implementation of RLHF

A modular RL library to fine-tune language models to human preferences

Train transformer language models with reinforcement learning.

No description.

Code for "Learning to summarize from human feedback"

No description.

The password hash Argon2, winner of PHC

No description.

Distilling Model Failures as Directions in Latent Space

High-Resolution Image Synthesis with Latent Diffusion Models

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

Distributionally robust neural networks for group shifts

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.

No description.

No description.

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

A framework for Privacy Preserving Machine Learning

Github pages backend for https://differentialprivacy.org

APPS: Automated Programming Progress Standard (NeurIPS 2021)

Official Python3 implementation of our ICML 2021 paper "Unbalanced minibatch Optimal Transport; applications to Domain Adaptation"

Learning to Execute

Code for "Differential Privacy Has Disparate Impact on Model Accuracy" NeurIPS'19

This repo implements several algorithms for learning with differential privacy.

No description.

Code for our ALiBi method for transformer language models.

Automatic metrics for GEM tasks

ACL'2021: LM-BFF: Better Few-shot Fine-tuning of Language Models

E2E NLG Challenge Evaluation metrics

No description.

Code for fast dpsgd implementations in JAX/TF

Library for training machine learning models with privacy for training data

🦄 State-of-the-Art Conversational AI with Transfer Learning

Prefix-Tuning: Optimizing Continuous Prompts for Generation

A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.

No description.

CodeBERT

No description.

No description.

Contains the code for our ICSE 2020 paper: Big Code != Big Vocabulary: Open-Vocabulary Language Models for Source Code and for its earlier pre-print: Maybe Deep Neural Networks are the Best Choice for Modeling Source Code (https://arxiv.org/abs/1903.05734). This is the first open vocabulary language model for code that uses the byte pair encoding algorithm (BPE) to learn a segmentation of code tokens into subword units.

:snake: Complete C99 parser in pure Python

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Data and Code for Reproducing "Global Relational Models of Source Code"

A dataset of 15 million CAD sketches with geometric constraint graphs.

No description.

Fast, general, and tested differentiable structured prediction in PyTorch

Pytorch implementation of KFAC and E-KFAC (Natural Gradient).

Image Markov Chain Monte Carlo

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.