Fin-R1

No tagged releases. Repository created Mar 11, 2025.

What it is

Fin-R1 from SUFE's AI-FLM lab is a 7B-parameter model trained in two stages (supervised fine-tuning, then reinforcement learning) on financial reasoning data. It is a compact alternative to frontier models for structured financial reasoning and runs on a single GPU.

In the maintainers' words: “Fin-R1 is a large language model for complex financial reasoning developed and open-sourced with the joint efforts of the SUFE-AIFLM-Lab at the School of Statistics and Data Science, Shanghai University of Finance and Economics and FinStep.AI.”