SPLADE-PT-BR is a fine-tuned version of the SPLADE model for Portuguese text retrieval. It learns to expand queries and documents with relevant terms while producing sparse vectors that remain highly interpretable and efficient for inverted-index based search. The model was trained on Portuguese QA datasets and is provided as an open-source Hugging Face model for use in information retrieval pipelines.
Splade Pt Br is an Other AI project. It focuses on retrieving relevant Portuguese documents using sparse lexical and semantic expansion without dense vector search. It is built as an open-source project for developers. Splade Pt Br is open source under the Apache-2.0 license. It runs on the web, the command line, and API.
Behind Splade Pt Br is AxelPCG, based in Brazil, and it first shipped in 2025. Among its 4 catalogued features are Sparse Retrieval, Query Expansion, and Portuguese Support.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do