jiangnanboy/llm_security

Stars
1
Language
Java
License
MIT License
Created 3 months ago
Updated 3 months ago

jiangnanboy/llm_security

jiangnanboy

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

利用分类法和敏感词检测法对生成式大模型的输入和输出内容进行安全检测，尽早识别风险内容。The input and output contents of generative large model are checked by classification method and sensitive word detection method to identify content risk as early as possible.

learning_to_rank

利用lightgbm做(learning to rank)排序学习，包括数据处理、模型训练、模型决策可视化、模型可解释性以及预测等。Use LightGBM to learn ranking, including data processing, model training, model decision visualization, model interpretability and prediction, etc.

albert_lstm_crf_ner

albert + lstm + crf实体识别，pytorch实现。识别的主要实体是人名、地名、机构名和时间。albert + lstm + crf (named entity recognition)

movie_knowledge_graph_app

电影知识图谱，主要包括实体识别、实体查询、关系查询以及智能问答等。movie knowledge graph(Entity identification, graph display, and intelligent question and answer)

education_knowledge_graph_app

Education knowledge graph(graph display, knowledge point tracking, intelligent question and answer，questions knowledge point prediction)。k12教育学科知识图谱，图谱展示，知识点追踪，智能问答以及题目知识点预测。

intent_detection_and_slot_filling

intent detection and slot filling 意图识别与槽填充联合模型

Jupyter Notebook

spark_data_mining

spark tutorial for big data mining。包括app流量运营分析、als推荐、smote样本采样、RFM客户价值分群、AHP层次分析客户价值得分、手机定位数据商圈挖掘、马尔可夫智能邮件预测、时序预测、关联规则、推荐电影好友等。

movie_kg

基于知识图谱的电影智能问答。neo4j构建电影图谱，spark ml完成问答意图分类，将问答语句转为cypher查询语句完成匹配查询。

recommendation_methods

个性化推荐模型，主要包括als、als_wr、biaslfm、lfm、nmf、svdpp、基于内容、基于内容回归、user-cf、item-cf、slopeone、关联规则以及基于内容和cf的混合等模型。

java-springboot-paddleocr

本项目利用java加载paddle-ocr的C++编译的exe文件，并利用springboot进行web部署访问。This project loads the C++ compiled version of paddle-ocr in java and makes use of springboot for web deployment.

intelligent_medical

intelligent medical，智慧医疗，包括疾病搜索、相关推荐、疾病医疗问答以及智能疾病诊断等功能。

gnn4lp

gnn for link prediction，图神经网络用于链接预测。

python_search

利用sklearn和gensim中的tfidf,lsa,doc2vec进行查询与文档匹配搜索

jcorrector

jcorrector 中文文本纠错工具， Text Error Correction Tool，Spelling Check

albert_re

albert-fc for RE(Relation Extraction)，中文关系抽取

java-springboot-paddleocr-v2

本项目利用JNI加载paddle-ocr的C++编译的dll库，并利用springboot进行web部署访问。This project uses JNI to load the C++ compiled dll libraries of paddle-ocr, and uses springboot for web deployment

punctuation_prediction

chinese sentence punctuation prediction，中文句子标点符号预测。

knowledge-automatic-tagging

题目知识点预测标注。Question knowledge point prediction.

Jupyter Notebook

text_grapher

利用java对文章进行分析并图谱化展示（主要提取关键词、实体、依存分析等）。

gcn_for_prediction_of_protein_interactions

gcn for prediction of protein interactions，图卷积用于蛋白质相互作用。

text_generation

Title and keywords are used to generate text.

model2onnx

model2onnx，将roberta和macbert模型转为onnx格式，并进行推理。

intent_classification

深度网络实现意图分类。

Jupyter Notebook

chatbot_chinese

Chinese chatbot for neural machine translation in PyTorch.Including basic seq2seq、seq2seq with attention、pointer generator、seq2seq with cnn and so on.

t5-onnx-corrector

t5-model-onnx，中文拼写纠错，Chinese spelling correction。

onnx-java

onnx-java，这里利用java加载onnx模型，并进行推理。

macbert-java-onnx

MacBERT for Chinese Spelling Correction, macbert中文拼写纠错

NewsSummary

一个改进的新闻摘要程序(an improved method of news summary)

CNN4IE

Chinese Information Extraction Toolkit。中文信息抽取工具。利用CNN各种变体进行实体抽取。

chinese_sentence_paraphrase

sentence paraphrase

albert_link_prediction

albert-fc for LP(Link Prediction)，中文实体链接预测

AutoText

智能文本自动处理工具（Intelligent text automatic processing tool）。AutoText的功能主要有文本纠错，图片ocr、版面检测以及表格结构识别等。The main functions of this project include text error correction, ocr, layout-detection and table structure recognition.

sentence_rewriting

chinese sentence rewriting

knowledge_point_graph

spark neo4j java 知识图谱数据处理

layout_analysis

中文版面检测（Chinese layout detection），yolov8 is used to detect the layout of Chinese document images。

albert_ner

albert-crf for NER(Named Entity Recognition)，中文实体识别。

text-de-duplication

text de-duplication 文本去重

pdf_to_docx

ocr，pdf转docx，pdf to docx

albert_srl

albert-crf for SRL(Semantic Role Labeling)，中文语义角色标注。

layout_analysis4j

利用java-yolov8实现版面检测（Chinese layout detection），java-yolov8 is used to detect the layout of Chinese document images

gec_check_template

grammatical correction，中文语法纠错模板

chatbot

pytorch前馈网络分类预测chatbot

Jupyter Notebook

j4nlp

java for nlp，java自然语言处理

triple_event_extract

EventExtraction & TriplesExtraction，复合事件抽取，依存关系三元组抽取

bert_ndcg_lp

bert-ndcg for LP(Link Prediction)，链接预测

easyKG

deep learning of knowledge graph ，知识图谱深度学习相关技术

entropy_sim

利用熵计算查询与文档的相关性。Entropy is used to calculate the relevance of a query to a document. This program is mainly based on 《Content-based relevance estimation on the web using inter-document similarities》(2012-CIKM).

llm_corpus_quality

大模型预训练中文语料清洗及质量评估 Large model pre-training corpus cleaning

RecomSys

A simple recommendation system

table_ocr_java

TABLE DETECTION IN IMAGES AND OCR TO CSV WITH JAVA

micrograd4j

A micro scalar-valued Autograd engine developed with java, and a neural net library on top of it.

similarity_words

计算词间的相关性，并进行图谱化展示。calculate the relevance between words

vehicle_license_plate_recognition

车牌识别（vehicle license plate recognition)

pediatrics_llm_qa

Small model of pediatric consultation

semantic_matching

semantic matching，语义匹配

Jupyter Notebook

doc_ai

这里将paddle中的ocr等模型转为onnx格式，并利用java版深度框架djl加载这些onnx模型进行推理预测尝试。

spark-smote

The program uses spark to implement smote sampling.利用spark实现训练样本smote采样。