stanleylsx / text_embeddingLinks
一个用于训练句子embedding的工具,支持Cosent以及Simcse、infonce
☆21Updated 7 months ago
Alternatives and similar repositories for text_embedding
Users that are interested in text_embedding are comparing it to the libraries listed below
Sorting:
- 🌈 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。☆117Updated 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☆83Updated 3 years ago
- 基于pytorch的百度UIE命名实体识别。☆57Updated 3 years ago
- sentence-transformers to onnx 让sbert模型推理效率更快☆166Updated 3 years ago
- 通用版面分析 | 中文文档解析 |Document Layout Analysis | layout paser☆48Updated last year
- deep training task☆30Updated 2 years ago
- 一个基于预训练的句向量生成工具☆138Updated 2 years ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆110Updated 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☆133Updated last year
- llama信息抽取实战☆102Updated 2 years ago
- Knowledge Graph☆176Updated 3 years ago
- SMP 2023 ChatGLM金融大模型挑战赛 60 分baseline思路介绍☆186Updated 2 years ago
- SinglepassTextCluster, an TextCluster tools based on Singlepass cluster algorithm that use tfidf vector and doc2vec,which can be used for…☆65Updated 4 years ago
- 基于模板的文本纠错;Automatically Mining Error Templates for Grammatical Error Correction☆44Updated 3 years ago
- basic framework for rag(retrieval augment generation)☆86Updated 2 years ago
- ChatGLM-6B fine-tuning.☆136Updated 2 years ago
- BLOOM 模型的指令微调☆24Updated 2 years ago
- Minimal keyword extraction with BERT☆89Updated 4 years ago
- 中文文本纠错模型,keras实现☆75Updated 4 years ago
- 超长文本分类(大于1000字);文档级/篇章级文本分类;主要是解决长距离依赖问题☆131Updated 4 years ago
- 基于pytorch的中文意图识别和槽位填充☆212Updated 6 months ago
- LLM for NER☆80Updated last year
- 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☆75Updated last year
- experiments of some semantic matching models and comparison of experimental results.☆163Updated 3 months ago
- 3000000+语义理解与匹配数据集。可用于无监督对比学习、半监督学习等构建中文领域效果最好的预训练模型☆311Updated 3 years ago
- 任务型对话系统(Task-based Dialogue System)☆66Updated 4 years ago
- GlobalPointer的优化版/NER实体识别☆122Updated 4 years ago
- (1)弹性区间标准化的旋转位置词嵌入编码器+peft LORA量化训练,提高万级tokens性能支持。(2)证据理论解释学习,提升模型的复杂逻辑推理能力(3)兼容alpaca数据格式。☆45Updated 2 years ago
- 使用qlora对中文大语言模型进行微调,包含ChatGLM、Chinese-LLaMA-Alpaca、BELLE☆89Updated 2 years ago
- 中文文本分类、序列标注工具包(pytorch),支持中文长文本、短文本的多类、多标签分类任务,支持中文命名实体识别、词性标注、分词、抽取式文本摘要等序列标注任务。 Chinese text classification and sequence labeling toolk…☆354Updated last year