NiuTrans Open Source

All

19 repositories

LaMaTE
Public
Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation
Python
•
MIT License
•1•18•0•0•Updated Mar 11, 2025Mar 11, 2025
ABigSurveyOfLLMs
Public
A collection of 150+ surveys on LLMs
Creative Commons Zero v1.0 Universal
•19•272•0•0•Updated Feb 19, 2025Feb 19, 2025
NiuLoad
Public
Python
•1•4•1•0•Updated Nov 8, 2024Nov 8, 2024
Vision-LLM-Alignment
Public
This repository contains the code for SFT, RLHF, and DPO, designed for vision-based LLMs, including the LLaVA models and the LLaMA-3.2-vision models.
vision alignment multi-model reward ppo sft dpo llm rlhf mllm
Python
•8•104•1•0•Updated Oct 16, 2024Oct 16, 2024
ForgettingCurve
Public
A benchmark for testing memorization abilities of LMs
Python
•1•20•1•0•Updated Oct 15, 2024Oct 15, 2024
MTBook
Public
《机器翻译：基础与模型》肖桐朱靖波著 - Machine Translation: Foundations and Models
machine-learning natural-language-processing deep-learning neural-machine-translation statistical-machine-translation tex machine-translation
TeX
•762•2.8k•3•1•Updated Sep 14, 2024Sep 14, 2024
NiuTrans.SMT
Public
NiuTrans.SMT is an open-source statistical machine translation system developed by a joint team from NLP Lab. at Northeastern University and the NiuTrans Team. The NiuTrans system is fully developed in C++ language. So it runs fast and uses less memory. Currently it supports phrase-based, hierarchical phrase-based and syntax-based (string-to-tre…
parsing machine-translation phrase-based-translation decoder statistical-machine-translation
C++
•
GNU General Public License v2.0
•36•152•0•0•Updated Jul 17, 2024Jul 17, 2024
Classical-Modern
Public
非常全的文言文（古文）-现代文平行语料
corpus traditional-chinese parallel-corpus traditional-and-simplified-chinese
Python
•
MIT License
•301•1.3k•5•0•Updated Apr 21, 2024Apr 21, 2024
ABigSurvey
Public
A collection of 1000+ survey papers on Natural Language Processing (NLP) and Machine Learning (ML).
machine-learning natural-language-processing deep-learning neural-networks surveys paper-list
GNU General Public License v3.0
•245•2k•1•3•Updated Mar 31, 2024Mar 31, 2024
Hands-on-GEMM
Public
A tutorial on GEMM
Cuda
•
GNU General Public License v3.0
•3•8•0•0•Updated Mar 18, 2024Mar 18, 2024
NiuTrans.NMT
Public
A Fast Neural Machine Translation System developed in C++.
machine-translation transformer neural-machine-translation fast-decoding
C++
•
Apache License 2.0
•38•139•4•0•Updated Mar 7, 2024Mar 7, 2024
Introduction-to-Transformers
Public
An introduction to basic concepts of Transformers and key techniques of their recent advances.
natural-language-processing deep-learning transformers
Creative Commons Zero v1.0 Universal
•3•49•0•0•Updated Dec 21, 2023Dec 21, 2023
CNSurvey
Public
一份中文综述文章列表（自然语言处理&机器学习）
machine-learning natural-language-processing deep-learning surveys
Creative Commons Zero v1.0 Universal
•92•564•0•0•Updated May 26, 2023May 26, 2023
compiler-notes
Public
6•67•0•0•Updated Mar 24, 2023Mar 24, 2023
MTVenues
Public
A list of conferences and journals relevant to machine translation
Creative Commons Zero v1.0 Universal
•7•33•0•0•Updated Mar 17, 2022Mar 17, 2022
NiuTensor
Public
NiuTensor is an open-source toolkit developed by a joint team from NLP Lab. at Northeastern University and the NiuTrans Team. It provides tensor utilities to create and train neural networks.
machine-learning deep-learning artificial-neural-networks tensor
C++
•
Apache License 2.0
•174•382•0•0•Updated Nov 6, 2021Nov 6, 2021
NASPapers
Public
Paper lists of neural architecture search (NAS)
machine-learning deep-learning neural-networks neural-architecture-search nas
Creative Commons Zero v1.0 Universal
•23•130•0•0•Updated Sep 3, 2021Sep 3, 2021
LanguageCodes
Public
We present a list of languages with their codes, families, regions and etc. We also present a list of multi-lingual corpora (with urls).
multi-lingual corpus language-codes
Creative Commons Zero v1.0 Universal
•25•83•0•0•Updated Jun 2, 2021Jun 2, 2021
MT-paper-lists
Public
MT paper lists (by conference)
neural-machine-translation paper-list machine-translation
BSD 3-Clause "New" or "Revised" License
•52•122•1•2•Updated Dec 7, 2020Dec 7, 2020