unknown

DeepAnalyze is an open-source agentic large language model designed for autonomous data science workflows. Built on DeepSeek-R1-0528-Qwen3-8B, it autonomously handles the entire data science pipeline including data preparation, analysis, modeling, visualization, and report generation across structured, semi-structured, and unstructured data sources. The project includes a fully open-sourced 8B parameter model, 500K instruction dataset for training, deployment scripts with vLLM, and a web-based demo interface. It supports curriculum-based agentic training with reinforcement learning and provides unified evaluation frameworks for data science benchmarks.

ruc-datalab/DeepAnalyze: DeepAnalyze is the first agentic LLM for autonomous data science.

Become a cool developer with Dev Source! Your ultimate dev source for resources, insights, and a thriving community to learn, grow, and stay ahead every single day!