#190 · Primary category： MLOps & Evaluation
PIXIU
Open-source suite of financial large language models, instruction-tuning data, and evaluation benchmarks for holistic assessment of financial AI.
Project last updated：03/04/25
GitHub Stars
884
Forks
122
Contributors
14
License
MIT
Why we included this project
PIXIU is one of the few finance-focused LLM resources that takes evaluation seriously, bundling the FinMA family of 7B checkpoints with an instruction-tuning dataset and FLUE, a benchmark that covers sentiment analysis, entity recognition, question answering over financial documents, summarization, and credit scoring. That makes it a practical yardstick for researchers comparing model variants and for engineering teams who want to sanity-check a finance-specific model before real use. The benchmark also includes Chinese and Spanish variants, which helps teams building multilingual fintech products. Keep in mind the repo's own disclaimer: this is an academic resource, so treat it as a research and validation toolkit, not a drop-in production component.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
unsloth
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, FLUX and more.
LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
airflow
Apache Airflow - A platform to programmatically author, schedule, and monitor workflows
langfuse
🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
netron
Visualizer for neural network, deep learning and machine learning models