google/datagemma-rig-27b-it

DataGemma RIG 27B-IT is a fine-tuned Gemma 2 model developed by Google, designed to integrate reliable public statistical data from Data Commons into LLM responses. This instruction-tuned model specializes in a retrieval interleaved generation (RIG) approach, annotating generated text with natural language queries to Data Commons for statistical verification. It excels at providing contextually relevant statistical data within generated text, making it suitable for applications requiring factual accuracy from external data sources.