pemywei

csanmt

This is a code repository for the ACL 2022 paper "Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation"

basic-encoder-decoder

A simple implementation of encoder-decoder for nmt.

MSC-NMT

Code and materials for Multiscale Collaboration Deep Models for Neural Machine Translation

academicpages.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

chatgpt_system_prompt

store all agent's system prompt

Chinese-LLaMA-Alpaca

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

fairseq

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

fast-transformers

Pytorch library for fast transformer implementations

FastChat

An open platform for training, serving, and evaluating large languages. Release repo for Vicuna and FastChat-T5.

horovod

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

ICLR2021-OpenReviewData

Crawl & visualize ICLR papers and reviews.

LeetCodeAnimation

Demonstrate all the questions on LeetCode in the form of animation.（用动画的形式呈现解LeetCode题目的思路）

llama

Inference code for LLaMA models

Megatron-LLM

distributed trainer for LLMs

MOSS-RLHF

MOSS-RLHF

MTBook

《机器翻译：统计建模与深度学习方法》肖桐 朱靖波 著 - "Machine Translation: Statistical Modeling and Deep Learning Methods" by Tong Xiao and Jingbo Zhu

pemywei.github.io

Xiangpeng Wei's home page

pretrained-models

Open Language Pre-trained Model Zoo

QuRating

Selecting High-Quality Data for Training Language Models

Qwen-7B

ShadowsocksX-NG

Next Generation of ShadowsocksX

transformers

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

ucasthesis

[最新样式] **科学院大学学位论文 LaTeX 模板 LaTeX Thesis Template for the University of Chinese Academy of Sciences

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

VOLT

Code for paper "Vocabulary Learning via Optimal Transport for Neural Machine Translation"

wengrx.github.io

homepage

WMT20SrcDA

Code and issue tracker for WMT20 source-based DA campaigns

xtreme

XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 typologically diverse languages and includes nine tasks.

ZIP