Hugging Face Overview
FINGU-AI/FinguAI-Chat-v1: Multilingual Financial & Legal Chat Model
FinguAI-Chat-v1, developed by Grinda AI Inc., is a 0.6 billion parameter causal language model fine-tuned from Qwen/Qwen1.5-0.5B-Chat. It is specifically designed to provide expertise in finance, investment, and legal frameworks, with a strong focus on English, Korean, and Japanese languages.
Key Capabilities
- Multilingual Financial & Legal Expertise: Offers specialized knowledge in global financial markets and regulatory landscapes across English, Korean, and Japanese contexts.
- Language Proficiency Enhancement: Aims to improve language skills for effective communication within finance and legal domains.
- Career Advancement Support: Provides knowledge and skills relevant for careers in investment banking, corporate finance, asset management, and regulatory compliance.
Training Details
The model was fine-tuned using supervised fine-tuning with the TrL Library and Transformer. The training dataset comprised 9042 samples, with approximately 3000 samples each in Korean, English, and Japanese, ensuring robust multilingual performance in its specialized domains.
Use Cases
This model is particularly well-suited for applications requiring:
- Financial Information Retrieval: Answering questions related to finance, investment strategies, and market trends.
- Legal Framework Understanding: Providing insights into regulatory compliance and legal aspects within financial sectors.
- Multilingual Communication: Assisting users in understanding and communicating financial and legal concepts across English, Korean, and Japanese.