If you're trying to find the right model on Hugging Face, go to the Models menu and you'll find a list of tasks by which you can search for your model.
In deepset Cloud, there are two types of pipeline nodes that use models: dense retrievers and readers. Readers use models for question answering, while retrievers use sentence similarity or DPR models. For information about choosing the models for pipeline nodes, see EmbeddingRetriever, DensePassageRetriever, and Reader.
If you don't know which model to start with, you can use one of the models we recommend.
This table describes the models that we recommend for the Question Answering task:
|https://huggingface.co/deepset/roberta-base-squad2-distilled||A distilled model, relatively fast and with good performance.||English|
|https://huggingface.co/deepset/roberta-large-squad2||A large model with good performance. Slower than the distilled one.||English|
|https://huggingface.co/deepset/xlm-roberta-base-squad2||A base model with good speed and performance.||Multilingual|
|https://huggingface.co/deepset/tinyroberta-squad2||A very fast model.||English|
You can also view state-of-the-art question answering models on the HuggingFace leaderboard.
This table describes the models that we recommend for the Information Retrieval task:
|https://huggingface.co/sentence-transformers/all-mpnet-base-v2||A model with good speed and performance.||English|
|https://huggingface.co/sentence-transformers/multi-qa-mpnet-base-dot-v1||A model with good speed and performance.||English|
|https://huggingface.co/sentence-transformers/all-MiniLM-L12-v2||A model faster than the base models with still good performance.||English|
|https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2||A fast multilingual model.||Multilingual|
|https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2||A relatively big model, slower than the mini one but with better performance.||Multilingual|
To use a model, simply provide its Hugging Face location as a parameter to the node and deepset Cloud will take care of loading it. For example:
- name: Retriever type: EmbeddingRetriever params: document_store: DocumentStore embedding_model: sentence-transformers/multi-qa-mpnet-base-dot-v1 model_format: sentence_transformers pooling_strategy: cls_token top_k: 20
Updated about 2 months ago