how to load a .w2v format saved model in databricks

[data_scientist]

Hi,

I am trying load a pre-trained word2vec model which has been saved in .w2v format in databricks. I am not able to load this file . Help me with the correct command.

[Anonymous]

Hi there and welcome to the community! My name is Piper, and I'm a moderator for the community. 🙂

Thank you for coming to us with your question. We will give it a bit to see how your peers respond and then we will circle back if we need to.

[Kaniz · Accepted solution]

Hi @sonam de​ , To save models, use the MLflow functions log_model and save_model. You can also save models using their native APIs onto Databricks File System (DBFS). For MLlib models, use ML Pipelines.

To export models for serving individual predictions, you can use MLeap, a common serialization format and execution engine for machine learning pipelines. MLeap supports serializing Apache Spark, scikit-learn, and TensorFlow pipelines into a bundle, so you can load and deploy trained models to make predictions with new data. You can import the exported models into both Spark and other platforms for scoring and predictions.

• MLeap ML model export

Source