colbert_scores_top_p

Computes the ColBERT scores between queries and documents embeddings using top-p sampling.

Parameters

• queries_embeddings (torch.Tensor)

  The queries embeddings. Shape: (batch_size, num_tokens_queries, embedding_size)

• documents_embeddings (torch.Tensor)

  The documents embeddings. Shape: (batch_size, num_tokens_documents, embedding_size)

• mask (torch.Tensor) – defaults to None

  Optional mask tensor. Default is None.

• p (float) – defaults to 0.001

  The cumulative probability threshold for top-p sampling. Default is 0.005.