[Question]: 想知道问答系统中这些模型可选的列表谢谢

[1042312930]

请提出你的问题

下面这些模型的可选列表,更换的时候不知道自己是否填写正确 query_embedding_model: rocketqa-zh-nano-query-encoder passage_embedding_model: rocketqa-zh-nano-query-encoder model_name_or_path: ernie-gram-zh-finetuned-dureader-robust model_name_or_path: rocketqa-zh-dureader-cross-encoder

能去修改下面的代码 components: # define all the building-blocks for Pipeline

• name: DocumentStore type: ElasticsearchDocumentStore # consider using MilvusDocumentStore or WeaviateDocumentStore for scaling to large number of documents params: host: localhost index: baike_cities embedding_dim: 312 embedding_dim: 768 port: 9200
• name: Retriever type: DensePassageRetriever params: document_store: DocumentStore # params can reference other components defined in the YAML top_k: 10 query_embedding_model: rocketqa-zh-nano-query-encoder passage_embedding_model: rocketqa-zh-nano-query-encoder query_embedding_model: rocketqa-zh-base-query-encoder passage_embedding_model: rocketqa-zh-base-para-encoder embed_title: False
• name: Ranker # custom-name for the component; helpful for visualization & debugging type: ErnieRanker # pipelines Class name for the component params: model_name_or_path: rocketqa-zh-dureader-cross-encoder model_name_or_path: rocketqa-zh-base-cross-encoder top_k: 5
• name: Reader # custom-name for the component; helpful for visualization & debugging type: ErnieReader # pipelines Class name for the component params: model_name_or_path: ernie-gram-zh-finetuned-dureader-robust model_name_or_path: ernie-gram-zh-finetuned-base-robust context_window_size: 1000 return_no_answer: true top_k: 5

[1042312930]

我自己找到了在 https://github.com/PaddlePaddle/PaddleNLP/blob/develop/pipelines/API.md