stanleylsx / text_embedding
一个用于训练句子embedding的工具,支持Cosent以及Simcse
☆17Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for text_embedding
- 百度UIE抽取模型torch版训练预测框架☆11Updated last week
- 使用sentence-transformers(SBert)训练自己的文本相似度数据集并进行评估。☆45Updated 3 years ago
- 基于向量召回的检索式对话系统解决方案,dense retrieval,FAQ……☆32Updated 2 years ago
- benchmark of KgCLUE, with different models and methods☆26Updated 2 years ago
- deep training task☆29Updated last year
- 🌈 NERpy: Implementation of Named Entity Recognition using Python. 命名实体识别工具,支持BertSoftmax、BertSpan等模型,开箱即用。☆112Updated 8 months ago
- Finetune baichuan pretrained model with QLora method☆15Updated last year
- 通用版面分析 | 中文文档解析 |Document Layout Analysis | layout paser☆45Updated 4 months ago
- 基于simcse的中文句向量生成☆15Updated 2 years ago
- BLOOM 模型的指令微调☆24Updated last year
- Llama2-SFT, Llama-2-7B微调(transformers)/LORA(peft)/推理☆21Updated last year
- NLP tools, word segmentation, sentence segmentation, New-Word-Discovery,新词发现☆24Updated 9 months ago
- SinglepassTextCluster, an TextCluster tools based on Singlepass cluster algorithm that use tfidf vector and doc2vec,which can be used for…☆62Updated 3 years ago
- 中文标注工具,支持NER、文本分类、关系标注、对话标注等。☆61Updated 3 months ago
- 文本相似度,语义向量,文本向量,text-similarity,similarity, sentence-similarity,BERT,SimCSE,BERT-Whitening,Sentence-BERT, PromCSE, SBERT☆68Updated 6 months ago
- 基于torch的,支持logits、crf、span、global_pointer四种方法的命名实体识别任务框架☆17Updated 8 months ago
- [Unofficial] Predict code for AAAI 2022 paper: Unified Named Entity Recognition as Word-Word Relation Classification☆50Updated 2 years ago
- 使用torch整合两种经典的指针NER抽取范式,分别是SpanBert和苏神的GlobalPointer,简单加了些tricks,配置后一键运行☆131Updated 5 months ago
- 一个使用tensorflow2.3开发的基于Bert的意图识别的自然语言理解任务Demo☆24Updated 5 months ago
- use chatGLM to perform text embedding☆45Updated last year
- easy-bert是一个中文NLP工具,提供诸多bert变体调用和调参方法,极速上手;清晰的设计和代码注释,也很适合学习☆72Updated 2 years ago
- bert_avg,bert_whitening,sbert,consert,simcse,esimcse 中文句向量表示☆16Updated 2 years ago
- 有一个通用实体关系事件抽取的任务,需要使用到UIE模框架,而且需要将起部署到昇腾310服务器上,因为UIE模型底层使用的是ernie3.0,但是目前paddle官方还不支持ernie3.0模型在昇腾310上部署,所以才有了以下的操作,主要过程是,先试用paddle训练处模型…☆17Updated 2 years ago
- t5-model-onnx,中文拼写纠错,Chinese spelling correction。☆13Updated 2 years ago
- Sentence-Transformers Information Retrieval example on Chinese☆29Updated 8 months ago
- LLM for NER☆54Updated 3 months ago
- 意图槽位模型训练框架(单意图、独立槽位),使用的是JointBERT的结构进行编写,槽位提取时可以选择双指针(Binary Pointer)实体抽取和Global Pointer两种方法。☆17Updated 5 months ago
- using lear to do ner extraction☆29Updated 2 years ago