Year: 2026
Type: preprint
Abstract: We present FiMI (Finance Model for India), a domain-specialized financial language model developed by National Payments Corporation of India (NPCI) 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.
Source: arXiv (Cornell University)
Authors: Kathar, Aboli, Kumar, Aman, Kamath, Anusha, Srujan, Araveeti, Sharma, Ashish, Bhushan, Chandra, Sorate, Divya, Kumar, Duddu Prasanth, Acharya, Evan, Sharma, Harsh, Kadam, Hrithik, Singla, Kanishk, Doshi, Keyur, Praveen, Kiran, SK, Kolisetty Krishna, Adhikary, Krishanu, MPT, Lokesh, Sonowal, Mayurdeep, Shaikh, Nadeem, Prakash, Navya, Kothari, Nimit, Kukreja, Nitin, Devadiga, Prashant, Paul, Rakesh, Chauhan, Ratanjeet Pratap, Kalani, Raunak, Joshi, Raviraj, MH, Shamanth, Pandey, Shantanu, Soni, Shubham, Dixit, Siddharth, Jopat, Smriti, Patel, Sunil, Singh, Suraj, Paul, Suvradip, Pilla, Tulasi, Vaidya, Utkarsh, Nambiar, Vineeth, Kanvaty, Vishal, Dedhia, Yatharth
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7128021967
Cites:
Cited by:
Related to: