FiMI: A Domain-Specific Language Model for Indian Finance Ecosystem
AI 摘要
FiMI是为印度金融领域定制的领域专用语言模型,显著提升了金融推理和工具调用能力。
主要贡献
- 构建印度金融领域专用语言模型FiMI
- 在金融推理和工具调用任务上超越Mistral Small
- 维持通用基准测试性能
方法论
FiMI基于Mistral Small架构,通过多阶段训练,包括金融数据预训练、指令微调和领域监督微调。
原文摘要
We present FiMI (Finance Model for India), a domain-specialized financial language model developed for Indian digital payment systems. We develop two model variants: FiMI Base and FiMI Instruct. FiMI adapts the Mistral Small 24B architecture through a multi-stage training pipeline, beginning with continuous pre-training on 68 Billion tokens of curated financial, multilingual (English, Hindi, Hinglish), and synthetic data. This is followed by instruction fine-tuning and domain-specific supervised fine-tuning focused on multi-turn, tool-driven conversations that model real-world workflows, such as transaction disputes and mandate lifecycle management. Evaluations reveal that FiMI Base achieves a 20% improvement over the Mistral Small 24B Base model on finance reasoning benchmark, while FiMI Instruct outperforms the Mistral Small 24B Instruct model by 87% on domain-specific tool-calling. Moreover, FiMI achieves these significant domain gains while maintaining comparable performance to models of similar size on general benchmarks.