GitHub 热门项目：transformers-ruby

GitHub 项目：transformers-ruby 仓库地址：https://github.com/ankane/transformers-ruby 星级：730 | 作者：ankane 项目描述：最先进的 Ruby 变压器 =================================================== 自述文件内容： # 变形金刚.rb :slightly_smiling_face：Ruby 的最先进的 [transformers](https://github.com/huggingface/transformers) 为了快速推理，请查看 [Informers](https://github.com/ankane/informers) :fire: [](https://github.com/ankane/transformers-ruby/actions) ## 安装 首先，[安装 Torch.rb](https://github.com/ankane/torch.rb#installation)。 然后将此行添加到应用程序的 Gemfile 中： ``红宝石 宝石“变形金刚-rb” ```` ## 开始使用 - [模型](#models) - [管道](#pipelines) ## 型号 嵌入 - [sentence-transformers/all-MiniLM-L6-v2](#sentence-transformersall-MiniLM-L6-v2) - [句子变压器/multi-qa-MiniLM-L6-cos-v1](#sentence-transformersmulti-qa-MiniLM-L6-cos-v1) - [sentence-transformers/all-mpnet-base-v2](#sentence-transformersall-mpnet-base-v2) - [句子变压器/释义-MiniLM-L6-v2](#句子变压器释义-minilm-l6-v2) - [mixedbread-ai/mxbai-embed-large-v1](#mixedbread-aimxbai-embed-large-v1) - [thenlper/gte-small](#thenlpergte-small) - [intfloat/e5-base-v2](#intfloate5-base-v2) - [BAAI/bge-base-en-v1.5](#baaibge-base-en-v15) - [雪花/雪花-arctic-embed-m-v1.5](#snowflakesnowflake-arctic-embed-m-v15) 稀疏嵌入 - [opensearch-project/opensearch-neural-sparse-encoding-v1](#opensearch-projectopensearch-neural-sparse-encoding-v1) 重新排名 - [mixedbread-ai/mxbai-rerank-base-v1](#mixedbread-aimxbai-rerank-base-v1) - [BAAI/bge-reranker-base](#baaibge-reranker-base) ### 句子-transformers/all-MiniLM-L6-v2 [文档](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) ``红宝石 Sentences = ["这是例句","每个句子都被转换"] model = Transformers.pipeline("embedding", "sentence-transformers/all-MiniLM-L6-v2") 嵌入=模型。（句子） ```` ### 句子转换器/multi-qa-MiniLM-L6-cos-v1 [文档](https://huggingface.co/sentence-transformers/multi-qa-MiniLM-L6-cos-v1) ``红宝石 query =“有多少人住在伦敦？” docs = [“大约有 900 万人居住在伦敦”，“伦敦以其金融区而闻名”] model = Transformers.pipeline("embedding", "sentence-transformers/multi-qa-MiniLM-L6-cos-v1") query_embedding = 模型。（查询） doc_embeddings = 模型。（文档） 分数 = doc_embeddings.map { |e| e.zip(query_embedding).sum { |d, q| d * q } } doc_score_pairs = docs.zip(scores).sort_by { |d, s| -s} ```` ### 句子转换器/all-mpnet-base-v2 [文档](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) ``红宝石 Sentences = ["这是例句","每个句子都被转换"] model = Transformers.pipeline("嵌入", "sentence-transformers/all-mpnet-base-v2") 嵌入=模型。（句子） ```` ### 句子转换器/释义-MiniLM-L6-v2 [文档](https://huggingface.co/sentence-transformers/paraphrase-MiniLM-L6-v2) ``红宝石 Sentences = ["这是一个例句","每个句子都包含