Code for my PhD dissertation: Contextures: The mechanism of representation learning.

A distributed, extensible, secure solution for evaluating machine generated code with unit tests in multiple programming languages.

[ACL '24] Source code for paper: INTERVENOR : Prompt the Coding Ability of Large Language Models with the Interactive Chain of Repairing

CodeForces Algorithms

Convert between .srt and .fcpxml files for subtitles creation

FireFlyer Record file format, writer and reader for DL training samples.

Code repo for "Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers" (ACL 2023)

Tensorboard extension for Jupyterlab all in one

play hard code hard

HFAI deep learning models

AST Tokenizing Unparser: A Python unparser that unparses an AST into a sequence of Python tokens

Automatically exported from code.google.com/p/word2vec

KG-BERT: BERT for Knowledge Graph Completion

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

An Open-Source Package for Knowledge Embedding (KE)

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Extract annotated misspellings from MIMIC-III.

Tacotron2 with BERT examples

[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

[ECCV 2018] AMC: AutoML for Model Compression and Acceleration on Mobile Devices

BERT score for text generation

a Suite in Python for Computer-Assisted Music

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

IRL project

Convex Optimization: Assignment and Project