Model Types
Gretel's models can help you transform and synthesize your sensitive data to generate provably-private versions.
Last updated
Was this helpful?
Gretel's models can help you transform and synthesize your sensitive data to generate provably-private versions.
Last updated
Was this helpful?
Gretel offers the following synthetics models:
- Gretel’s flagship LLM-based model for generating privacy-preserving, real-world quality synthetic data across numeric, categorical, text, JSON, and event-based tabular data with up to ~50 columns.
Data types: Numeric, categorical, text, JSON, event-based
Differential privacy: Optional
Formerly known as: Navigator Fine Tuning
- Gretel’s model for generating privacy-preserving synthetic text using your choice of top performing open-source models.
Data types: Text
Differential privacy: Optional
Formerly known as: Gretel GPT
- Gretel’s model for quickly generating synthetic numeric and categorical data for high-dimensional datasets (>50 columns) while preserving relationships between numeric and categorical columns.
Data types: Numeric, categorical
Differential privacy: NOT supported
Formerly known as: ACTGAN
- Gretel’s model for generating differentially-private data with very low epsilon values (maximum privacy). It is best for basic analytics use cases (e.g. pairwise modeling), and runs on CPU. If your use case is training an ML model to learn deep insights in the data, Tabular Fine-Tuning is your best option.
Data types: Numeric, categorical
Differential privacy: Required; you cannot run without differential privacy
You can learn more about Gretel Synthetics models .
Gretel’s model combines data classification with data transformation to easily detect and anonymize or mutate sensitive data. Use this data classification to detect a variety of such as PII, in both structured and unstructured text.
We generally recommend combining Gretel Transform with Gretel Synthetics using to redact or replace sensitive data before training a synthetics model.
You can learn more about Gretel Transform .