Lisennlp's repositories
two_sentences_classifier
Bert分类,语义相似度,获取句向量。
bert_crf_sequence_annotation
基于Pytorch+BERT+CRF的NLP序列标注模型,目前包括分词,词性标注,命名实体识别等
distributed_train_pytorch
pytorch分布式训练,支持多机多卡,单机多卡。
chinese_word_disambiguation
中文词义消歧项目(Chinese WSD),基于LSTM + ATTENTION模型架构,Pytorch实现。代码简单,上手容易。
chinese_extraction_mrc
基于Pytorch + BERT的抽取式机器阅读理解
transformer-xl-learn
transformer-xl 简单运行代码,学习使用
GPT2-Chinese
中文GPT2预训练语言模型,直接运行
albert_pytorch
ALBERT: 缩小的BERT,但效果却比BERT好
big_vision
Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.
clustering
向量PCA,TSNE降维,K-means聚类
DC_DeepSC
Pytorch implementation of the DeepSC
Event-Extraction
基于法律裁判文书的事件抽取及其应用,包括数据的分词、词性标注、命名实体识别、事件要素抽取和判决结果预测等内容
flax
Flax is a neural network library for JAX that is designed for flexibility.
flaxformer
fork from google
gpt-neox-j
基于gpt-neox修改为支持huggingface的gptj训练
MaxText
TPU Multi Slice Test
mesh_easy_jax
mesh_transformer_jax + easylm train llama model
MetaICL
An original implementation of "MetaICL Learning to Learn In Context" by Sewon Min, Mike Lewis, Luke Zettlemoyer and Hannaneh Hajishirzi
NLP-SubjectExtract-relation
小说数据预处理
paxml_praxis
google paxml + praxis
praxis
learn use
ray-jax-tpu-pod-demos
Demos starting ray cluster on tpu pod
realworldnlp
Example code for "Real-World Natural Language Processing"
stopwords
中文常用停用词表(哈工大停用词表、百度停用词表等)
t5x
fork from google