Xuechen Li (lxuechen)

lxuechen

Geek Repo

Company:Stanford University

Home Page:www.lxuechen.com

Twitter:@lxuechen

Github PK Tool:Github PK Tool


Organizations
lxuechen-org
stanford-crfm
stanfordnlp
VectorInstitute

Xuechen Li's repositories

BDMC

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

Language:PythonLicense:MITStargazers:50Issues:3Issues:1

Differentially-Private-Fine-tuning-of-Language-Models

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

Language:PythonStargazers:2Issues:1Issues:0

apps

APPS: Automated Programming Progress Standard (NeurIPS 2021)

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

attention_with_linear_biases

Code for our ALiBi method for transformer language models.

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

captum

Model interpretability and understanding for PyTorch

Language:PythonLicense:BSD-3-ClauseStargazers:0Issues:1Issues:0

CodeBERT

CodeBERT

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

CrypTen

A framework for Privacy Preserving Machine Learning

Language:PythonLicense:MITStargazers:0Issues:1Issues:0
Language:LexLicense:MITStargazers:0Issues:1Issues:0

differential-privacy-vs-fairness

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

Language:PythonStargazers:0Issues:1Issues:0

Differentially-Private-Deep-Learning

This repo implements several algorithms for learning with differential privacy.

Language:PythonStargazers:0Issues:1Issues:0

differentialprivacy

Github pages backend for https://differentialprivacy.org

Language:HTMLLicense:MITStargazers:0Issues:1Issues:0

e2e-metrics

E2E NLG Challenge Evaluation metrics

Language:PythonLicense:NOASSERTIONStargazers:0Issues:1Issues:0

fast-dpsgd

Code for fast dpsgd implementations in JAX/TF

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

GEM-metrics

Automatic metrics for GEM tasks

Language:PythonLicense:MITStargazers:0Issues:1Issues:0
Language:PythonStargazers:0Issues:1Issues:0
Language:PythonLicense:MITStargazers:0Issues:1Issues:0

ICLR20-Great

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

Language:PythonStargazers:0Issues:1Issues:0

JUMBOT

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

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

LM-BFF

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

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

minGPT

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

Language:Jupyter NotebookLicense:MITStargazers:0Issues:1Issues:0

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.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

P-tuning

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

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

PrefixTuning

Prefix-Tuning: Optimizing Continuous Prompts for Generation

Language:PythonStargazers:0Issues:1Issues:0

privacy

Library for training machine learning models with privacy for training data

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

pycparser

:snake: Complete C99 parser in pure Python

Language:PythonLicense:NOASSERTIONStargazers:0Issues:1Issues:0

robustness

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

Language:Jupyter NotebookLicense:MITStargazers:0Issues:1Issues:0

SketchGraphs

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

Language:CudaLicense:MITStargazers:0Issues:1Issues:0
Language:TeXStargazers:0Issues:1Issues:0
Language:Jupyter NotebookStargazers:0Issues:1Issues:0

vissl

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

Language:Jupyter NotebookLicense:MITStargazers:0Issues:1Issues:0