shibing624 / similarities
Similarities: a toolkit for similarity calculation and semantic search. 相似度计算、匹配搜索工具包,支持亿级数据文搜文、文搜图、图搜图,python3开发,开箱即用。
☆792Updated 3 weeks ago
Alternatives and similar repositories for similarities:
Users that are interested in similarities are comparing it to the libraries listed below
- unified embedding model☆834Updated last year
- TextGen: Implementation of Text Generation models, include LLaMA, BLOOM, GPT2, BART, T5, SongNet and so on. 文本生成模型,实现了包括LLaMA,ChatGLM,BLO…☆937Updated 2 months ago
- The online version is temporarily unavailable because we cannot afford the key. You can clone and run it locally. Note: we set defaul ope…☆793Updated 5 months ago
- text2vec, text to vector. 文本向量表征工具,把文本转化为向量矩阵,实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型,开箱即用。☆4,519Updated 3 weeks ago
- PromptCLUE, 全中文任务支持零样本学习模型☆655Updated last year
- PaddleNLP UIE模型的PyTorch版实现☆602Updated last year
- 基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型,进行下游具体任务微调,涉及Freeze、Lora、P-tuning、全参微调等☆2,667Updated 11 months ago
- LexiLaw - 中文法律大模型☆728Updated last year
- An Open-sourced Knowledgable Large Language Model Framework.☆1,243Updated 5 months ago
- Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.☆970Updated 6 months ago
- 中文CLIP预训练模型☆396Updated last year
- Chat-甄嬛是利用《甄嬛传》剧本中所有关于甄嬛的台词和语句,基于ChatGLM2进行LoRA微调得到的模仿甄嬛语气的聊天语言模型。☆519Updated 2 months ago
- 雅意信息抽取大模型:在百万级人工构造的高质量信息抽取数据上进行指令微调,由中科闻歌算法团队研发。 (Repo for YAYI Unified Information Extraction Model)☆270Updated 3 months ago
- 多模态中文LLaMA&Alpaca大语言模型(VisualCLA)☆427Updated last year
- 一个简单快速的分词、命名实体识别工具☆541Updated 4 months ago
- 人工精调的中文对话数据集和一段chatglm的微调代码☆1,159Updated 6 months ago
- 大语言模型微调,Qwen2VL、Qwen2、GLM4指令微调☆213Updated last week
- MiniRBT (中文小型预训练模型系列)☆255Updated last year
- Netease Youdao's open-source embedding and reranker models for RAG products.☆1,496Updated 2 months ago
- 中文命名实体识别。包含目前最新的中文命名实体识别论文、中文实体识别相关工具、数据集,以及中文预训练模型、词向量、实体识别综述等。☆616Updated 6 months ago
- ChatGLM-6B 指令学习|指令数据|Instruct☆652Updated last year
- 本项目旨在收集开源的表格智能任务数据集(比如表格问答、表格-文本生成等),将原始数据整理为指令微调格式的数据并微调LLM,进而增强LLM对于表格数据的理解,最终构建出专门面向表格智能任务的大型语言模型。☆479Updated 7 months ago
- 使用peft库,对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调,并做lora model和base model的merge及4bit的量化(quantize)。☆356Updated last year
- RAG for Local LLM, chat with PDF/doc/txt files, ChatPDF. 纯原生实现RAG功能,基于本地LLM、embedding模型、reranker模型实现,无须安装任何第三方agent库。☆623Updated 2 months ago
- Unified Structure Generation for Universal Information Extraction☆900Updated 2 years ago
- [中文法律大模型] DISC-LawLLM: an intelligent legal system powered by large language models (LLMs) to provide a wide range of legal services.☆560Updated last month
- 基于开源embedding模型的中文向量效果测试☆125Updated last year
- chatglm 6b finetuning and alpaca finetuning☆1,539Updated 7 months ago
- Firefly中文LLaMA-2大模型,支持增量预训练Baichuan2、Llama2、Llama、Falcon、Qwen、Baichuan、InternLM、Bloom等大模型☆399Updated last year
- 为ChatGLM设计的微调数据集生成工具,速来制作自己的猫娘。☆596Updated 9 months ago