THE PROBLEM/CHALLENGE
Uhura Solutions is developing AI platform for document-driven process automation in financial services. The “Generative AI Intelligent Process Automation Platform – GAIPAP” project is a transformative initiative aimed at revolutionizing the financial industry through the integration of advanced AI-driven automation solutions that combine capabilities of Large Language Model (LLM), low-code development, and process automation workflows. This unique fusion of technologies holds the potential to significantly enhance operational efficiency, cost reduction, and customer experience within the financial sector.
The platform incorporates fine-tuned Large language models (LLMs), which sets it apart from generic AI solutions. These LLMs, refined for the financial industry’s unique language, context, and patterns, promise to deliver more precise and relevant insights. The platform’s value proposition is further strengthened by its ability to streamline workflows, offer scalability, real-time data insights, and elevate customer experiences. The integration of a low-code development framework and process automation workflows enables swift prototyping and deployment of AI-driven models, thereby accelerating time-to-market and capitalizing on market opportunities effectively.
SOLUTION
The project involves the use of open-source Python libraries and pre-trained Large language models which are fine-tuned on a custom-made private dataset created by the team, allowing for specialized tasks within the financial sector. Leonardo supercomputer enabled us to make a leap with GPU training experiments from 1B to 7B and higher Large language models. We are focusing on various LLM research and optimization methods in this phase of the project, which include hyperparameter tuning, model quantization and pruning, and parameter efficient fine-tuning (PEFT). Special attention is put on dataset preprocessing including quality filtering, deduplication and privacy redacting.
BENEFITS
- Through integrating fine-tuned LLMs with low-code automation workflows, the platform streamlines complex document-driven processes in the financial sector, significantly reducing manual effort and operational costs.
- Custom-trained LLMs on domain-specific datasets enable more precise and context-aware insights, enhancing decision-making and regulatory compliance in financial services.
- Leveraging HPC resources for large-scale model training and optimization allows rapid prototyping and deployment of AI solutions, helping financial institutions respond quickly to market demands.
This project was awarded with 4,500 node hours of GPU resources (8x64GB) on the Leonardo Buster HPC for a duration of 12 months. NCC Montenegro assisted Uhura in applying for and obtaining resources on the Leonardo HPC.