Language Models in deepset Cloud
deepset Cloud loads models directly from Hugging Face. You can use publically available models but also your private ones if you connect deepset Cloud with Hugging Face.
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, two types of pipeline nodes 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.
Models for Question Answering
This table describes the models that we recommend for the Question Answering task:
|deepset/roberta-base-squad2-distilled||A distilled model, relatively fast and with good performance.||English|
|deepset/roberta-large-squad2||A large model with good performance. Slower than the distilled one.||English|
|deepset/xlm-roberta-base-squad2||A base model with good speed and performance.||Multilingual|
|deepset/tinyroberta-squad2||A very fast model.||English|
You can also view state-of-the-art question answering models on the Hugging Face leaderboard.
Models for Information Retrieval
This table describes the models that we recommend for the Information Retrieval task:
|Model URL||Description||Language||Similarity Measure|
|sentence-transformers/all-mpnet-base-v2||A model with good speed and performance.||English||dot_product,|
|sentence-transformers/multi-qa-mpnet-base-dot-v1||A model with good speed and performance.||English||dot_product|
|sentence-transformers/all-MiniLM-L12-v2||A model faster than the base models with still good performance.||English||dot_product,|
|sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2||A fast multilingual model.||Multilingual||cosine|
|sentence-transformers/paraphrase-multilingual-mpnet-base-v2||A relatively big model, slower than the mini one but with better performance.||Multilingual||cosine|
For more information about these models, see sentence transformers.
Using a Model
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: DocumentStore type: DeepsetCloudDocumentStore params: similarity: dot_product # Make sure to choose the correct similarity function for the chosen Embedding model. - name: Retriever type: EmbeddingRetriever params: document_store: DocumentStore embedding_model: sentence-transformers/multi-qa-mpnet-base-dot-v1 model_format: sentence_transformers top_k: 20
Updated about 2 months ago