PIXIU
An open-source suite featuring financial large language models (FinMA), instruction datasets (FIT), and evaluation benchmarks (FinBen) for financial AI.
What is PIXIU?
PIXIU is an open-source project that provides a comprehensive suite for financial artificial intelligence, including the first financial large language models (FinMA), a multi-task instruction dataset (FIT), and a holistic evaluation benchmark (FinBen). It addresses the need for specialized, transparent tools to develop, fine-tune, and assess LLMs on financial tasks like sentiment analysis, question answering, and stock prediction.
AI researchers, data scientists, and financial technology developers working on applying large language models to financial domains such as quantitative analysis, risk assessment, and financial NLP.
PIXIU offers a fully open-source, holistic framework with specialized financial LLMs, diverse instruction data, and a rigorous multi-task benchmark, enabling reproducible research and development in financial AI without reliance on proprietary models.
Overview
This repository introduces PIXIU, an open-source resource featuring the first financial large language models (LLMs), instruction tuning data, and evaluation benchmarks to holistically assess financial LLMs. Our goal is to continually push forward the open-source development of financial artificial intelligence (AI).
Use Cases
Best For
- Fine-tuning large language models for financial sentiment analysis and news classification
- Evaluating LLM performance on financial NLP tasks like named entity recognition and relation extraction
- Building stock movement prediction models using multi-modal data (text and time-series)
- Developing credit scoring and fraud detection systems with LLMs
- Creating multi-lingual financial AI applications supporting English, Chinese, and Spanish
- Academic research on financial AI benchmarks and open-source LLM development
Not Ideal For
- Applications needing instant, API-based financial analysis without local model deployment and fine-tuning
- Small teams with limited GPU resources for training and inferencing 7B+ parameter models
- Production systems requiring plug-and-play financial tools with minimal setup and configuration
- Projects focused on niche financial domains not covered in FinBen's 30+ task benchmark
Pros & Cons
Pros
FinBen covers over 30 diverse tasks including sentiment analysis, QA, and stock prediction, with detailed performance metrics as shown in the tasks table and leaderboard.
Supports English, Chinese, and Spanish financial texts, and incorporates text, tables, and time-series data like stock prices for realistic scenarios, per the key features.
Provides all resources openly, including FinMA models, FIT datasets, and FinBen benchmarks, encouraging reproducible research and avoiding vendor lock-in.
Developed by multiple universities with papers published in venues like NeurIPS, ensuring credibility and ongoing updates, as noted in the citations and institution logos.
Cons
Requires Docker installation, manual BART checkpoint downloads, and configuration of Huggingface models, making initial deployment cumbersome for non-experts.
Labeled as v0.1 with some guides like 'How to fine-tune' marked 'coming soon', indicating potential bugs and lack of polished documentation.
FinMA models are 7B and 30B parameters, necessitating significant GPU memory and processing power, which may be prohibitive for resource-constrained teams.
Frequently Asked Questions
Related Projects
AI Hedge FundAn AI Hedge Fund Team
FinGPTFinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.
Hands-on LLMs: Train and Deploy a Real-time Financial Advisor🦖 𝗟𝗲𝗮𝗿𝗻 about 𝗟𝗟𝗠𝘀, 𝗟𝗟𝗠𝗢𝗽𝘀, and 𝘃𝗲𝗰𝘁𝗼𝗿 𝗗𝗕𝘀 for free by designing, training, and deploying a real-time financial advisor LLM system ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 𝘷𝘪𝘥𝘦𝘰 & 𝘳𝘦𝘢𝘥𝘪𝘯𝘨 𝘮𝘢𝘵𝘦𝘳𝘪𝘢𝘭𝘴
MarSMarS: a Financial Market Simulation Engine Powered by Generative Foundation Model
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.