TheFinAI/Fin-o1-14B is a 14 billion parameter language model developed by TheFinAI, fine-tuned from Qwen3-14B. This model is specifically optimized for financial reasoning tasks, leveraging SFT and GRPO training on a specialized financial dataset. It excels at complex financial mathematical reasoning, making it suitable for applications requiring precise financial analysis.
Loading preview...
Overview
TheFinAI/Fin-o1-14B is a 14 billion parameter language model, fine-tuned from the Qwen3-14B base model by TheFinAI. It has been specifically developed to enhance performance in financial reasoning tasks, utilizing Supervised Fine-Tuning (SFT) and Grouped Reinforcement Learning from Human Feedback (GRPO) training methods. The model's training involved a comprehensive dataset, TheFinAI/FinCoT, which is derived from various financial question-answering and reasoning benchmarks including FinQA, TATQA, DocMath-Eval, Econ-Logic, and BizBench-QA.
Key Capabilities
- Specialized Financial Reasoning: Designed to improve accuracy and understanding in complex financial contexts.
- Mathematical Reasoning: Enhanced for financial mathematical reasoning, crucial for analytical tasks.
- Robust Training: Benefits from SFT and GRPO on a diverse set of financial datasets, ensuring strong performance in its domain.
Good For
- Applications requiring precise financial analysis and interpretation.
- Tasks involving financial mathematical problem-solving.
- Research and development in financial AI, as detailed in their paper arxiv.org/abs/2502.08127.