Xuechen Li's repositories
Differentially-Private-Fine-tuning-of-Language-Models
Code for ICLR 2022 submission "Differentially Private Fine-tuning of Language Models".
attention_with_linear_biases
Code for our ALiBi method for transformer language models.
differential-privacy-vs-fairness
Code for "Differential Privacy Has Disparate Impact on Model Accuracy" NeurIPS'19
Differentially-Private-Deep-Learning
This repo implements several algorithms for learning with differential privacy.
differentialprivacy
Github pages backend for https://differentialprivacy.org
e2e-metrics
E2E NLG Challenge Evaluation metrics
fast-dpsgd
Code for fast dpsgd implementations in JAX/TF
GEM-metrics
Automatic metrics for GEM tasks
ICLR20-Great
Data and Code for Reproducing "Global Relational Models of Source Code"
OpenVocabCodeNLM
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.
PrefixTuning
Prefix-Tuning: Optimizing Continuous Prompts for Generation
robustness
A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.
SketchGraphs
A dataset of 15 million CAD sketches with geometric constraint graphs.