Supersymmetry Technology Releases BigBang Transformer [Qianyuan]: A 1 Billion Parameter Financial Large-Scale Pre-trained Language Model That Can Read Numbers Supersymmetry Technology has released the BigBang Transformer [Qianyuan], a 1 billion parameter financial large-scale pre-trained language model designed to enable pre-trained language models to understand numerical data.
**Intro: Linear Capital portfolio company Symmetry Tech releases 10-billion-parameter financial pre-trained language model BigBang Transformer [Qianyuan].** The BBT large model is built on a time-series-text cross-modal architecture, jointly training on textual and time-series data across two modalities. It improves downstream task accuracy by nearly 10% compared to T5 models of the same scale, and significantly increases the R2 score for time-series forecasting. The cross-modal architecture enables the language model to recognize temporal patterns —
![Supersymmetry Technology Releases BigBang Transformer [Qianyuan]: A 1 Billion Parameter Financial Large-Scale Pre-trained Language Model That Can Read Numbers
Supersymmetry Technology has released the BigBang Transformer [Qianyuan], a 1 billion parameter financial large-scale pre-trained language model designed to enable pre-trained language models to understand numerical data.](/_next/image?url=https%3A%2F%2Fkkcktdhgzddmdjdjoenc.supabase.co%2Fstorage%2Fv1%2Fobject%2Fpublic%2Fmedia%2Fimages%2F6c129a80-32b8-429f-8990-f331d11e0417%2F4d525ee4df1d.jpg&w=384&q=75)








