Google Unveils Gecko, a Versatile Text Embedding Model Distilled from Large Language Models

Gecko is trained on an LLM-generated synthetic dataset FRet that contains LLM-ranked positives and negatives.

The post Google Unveils Gecko, a Versatile Text Embedding Model Distilled from Large Language Models appeared first on Analytics India Magazine.

ai news & update analytics analytics india magazine dataset embedding gecko generated google india language language models large language large language model large language models llm magazine synthetic text text embedding