Edward-Sun

DIFUSCO

Code of NeurIPS paper: arxiv.org/abs/2302.08224

RECITE

Code of ICLR paper: https://openreview.net/forum?id=-cqvvvb-NkI

TSP-Detection

Code of ICCV paper: https://arxiv.org/abs/2011.10881

SLM

Code of EMNLP paper: http://aclweb.org/anthology/D18-1531

easy-to-hard

Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision

gpt-accelera

Simple and efficient pytorch-native transformer training and inference (batched)

structured-nart

TSM-PDE

Code of ICML paper arxiv.org/abs/2302.08105

NAT-EM

Code of ICML paper: https://arxiv.org/abs/2006.16378

Learning-to-Hash-Attention

Code of ICLR paper: https://openreview.net/forum?id=VGnOJhd5Q1q

Transformer-TPU

CMU MT & Seq2Seq Models Course Project

Robot

PKU OS Course Project

fairseq

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

GapBasedCWS

The implementation of https://arxiv.org/abs/1712.09509

alpaca_eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

anonymized-easy-to-hard

FastChat-Dromedary

FastChat customized for Dromedary with model parallel inference support

google-research

Google Research

promptsource

Toolkit for collecting and applying prompts

DeepSpeed-Dromedary

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

jax-cfd-1

Computational Fluid Dynamics in JAX

llama_hf_optimized

marian

Fast Neural Machine Translation in C++

ODE-DL

Paper List For Linking ODE and Deep Learning

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.