BGE-M3 model

**Overview**

The bge_m3 models are embedding models developed by Beijing Academy of Artificial Intelligence and packaged using MLflow’s sentence_transformers flavor. The models provided in this listing are

- [bge_m3](https://huggingface.co/BAAI/bge-m3)

Bge_m3 models are licensed under the [MIT License](https://github.com/FlagOpen/FlagEmbedding/blob/master/LICENSE). By installing this listing, you acknowledge and agree to the license.

For example notebooks of using the bge_m3 models in various use cases on Databricks, refer to [the Databricks ML example repository](https://github.com/databricks/databricks-ml-examples/tree/master/llm-models/embedding/bge/bge-m3).

**Use cases**

The bge_m3 models are embedding models that map text to low-dimensional vectors, and some example use cases are:
- RAG implementation
- Data visualization with clustering
- Semantic search document search engine

**Product details**

The embedding models in this listing can be deployed directly to Databricks Model Serving for immediate use, or loaded for fine-tuning or batch inference use cases. For more details, install the listing and view the provided model cards for each model.

搜集汇总

背景与挑战

背景概述

BGE-M3模型由北京人工智能研究院开发，采用MIT许可证，适用于文本嵌入任务如RAG实现、数据聚类和语义搜索。该模型支持在Databricks平台直接部署或进行批量推理和微调。