SEC-BERT is an open pretrained BERT model family specialized for financial text, including SEC filings. Developers and researchers can load its weights with Transformers for fill-mask, language-modeling, and downstream financial NLP tasks.
Sec Bert Base is a Classification & entity recognition project. It focuses on understanding and classifying financial text without training a language model from scratch. It is built as an open-source project for NLP researchers and financial machine-learning developers. Sec Bert Base is open source under the Apache-2.0 license. It ships for the web and API, and it can be self-hosted.
nlpaueb builds and maintains Sec Bert Base, and it first shipped in 2019. The project is developed in the open on GitHub with 11k stars and 18 commits in the last 90 days. Among its 7 catalogued features are fill-mask inference, pretrained weights, and transformers 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