zhajiahe's repositories
Token_Drop
Token Drop mechanism for Neural Machine Translation
MT-readings
Record papers reaing about MT. (机器翻译论文分享)
augmented-translation
Custom task for training Fairseq translation models with data augmentation (e.g. BPE-dropout).
autoencoder_demo
a demo for autoencoder
My_fairseq
My fairseq version
translation_demo
translation demo based on fairseq
ICPC_2010_Rain
Solution for ICPC 2010 H problem(rain).
JioNLP
无模型中文 NLP 工具包,飞速 NLP 开发,准确、高效、零使用门槛
lightseq
LightSeq: A High Performance Library for Sequence Processing and Generation
supWSD
supWSD is a supervised word sense disambiguation system. The flexible framework of supWSD allows users to combine different preprocessing modules, to select features extractors and choose which classifier to use. SupWSD is very light and has very small memory requirements. To configure the system, supWSD use a simple xml file.
Translation_Entropy
Tools for compute translation entropy of words
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs