Models from Microsoft, Partners, and Community

Models from Microsoft, Partners, and Community models are a select portfolio of curated models both general-purpose and niche models across diverse scenarios by developed by Microsoft teams, partners, and community contributors

• Managed by Microsoft: Purchase and manage models directly through Azure with a single license, world class support and enterprise grade Azure infrastructure
• Validated by providers: Each model is validated and maintained by its respective provider, with Azure offering integration and deployment guidance.
• Innovation and agility: Combines Microsoft research models with rapid, community-driven advancements.
• Seamless Azure integration: Standard Azure AI Foundry experience, with support managed by the model provider.
• Flexible deployment: Deployable as Managed Compute or Serverless API, based on provider preference.

Learn more about models from Microsoft, Partners, and Community

Key capabilities

About this model

Navigator Tabular is designed to democratize synthetic data generation while upholding high standards of responsible AI development. This purpose-built system creates diverse, domain-specific datasets at scales of hundreds to millions of examples while preserving complex statistical relationships and offering increased speed and accuracy compared to manual data creation.

Key model capabilities

• Natural language interface to specify data requirements
• Schema-based data generation
• Real-time and streaming data generation
• Dataset augmentation and modification
• Structured data supported as LLM inputs and outputs

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

• Creating synthetic data for LLM training and fine-tuning
• Generating evaluation datasets for AI models and RAG systems
• Augmenting limited training data with diverse synthetic samples
• Creating realistic PII/PHI data for model testing

Out of scope use cases

However, like any advanced AI system, Navigator Tabular may occasionally produce unexpected or biased outputs. We therefore recommend that users conduct appropriate testing and validation for their specific use cases. Fine-tuning capability for Gretel Navigator Tabular is not yet available on Azure AI.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

Agentic workflow system for synthetic data generation
Multi-modal support (tabular, text)
Scalable generation (up to millions of records)
Underlying LLMs fine-tuned by Gretel on 10 different industry data and formats including healthcare, life sciences, financial, manufacturing, retail

Training cut-off date

The provider has not supplied this information.

Training time

The provider has not supplied this information.

Input formats

Natural language interface to specify data requirements
Schema-based data generation
Structured data supported as LLM inputs and outputs

Output formats

Structured data supported as LLM inputs and outputs
Real-time and streaming data generation

Supported languages

The provider has not supplied this information.

Sample JSON response

The provider has not supplied this information.

Model architecture

Navigator Tabular employs a compound AI architecture specifically engineered for synthetic data, combining top open-source SLM models fine-tuned across 10+ industry domains.

Long context

The provider has not supplied this information.

Optimizing model performance

The provider has not supplied this information.

Additional assets

High-quality open synthetic datasets created using Navigator available on HuggingFace:

• Text-to-SQL Dataset : Large-scale dataset for SQL generation
• GSM8K Math Problem Solving Dataset : AI reasoning dataset
• Multilingual Financial PII Dataset : Financial services training data

Example Notebooks

Training disclosure

Training, testing and validation

Navigator Tabular is trained exclusively on high-quality, license-compliant datasets spanning 10+ sectors, ensuring both legal compliance and output quality.

Distribution

Distribution channels

The provider has not supplied this information.

More information

Navigator Tabular incorporates automated alignment checks to detect the generation of harmful or discriminatory data while respecting legitimate use cases across industries. Gretel's governance framework includes privacy-preserving architecture, regular security audits, and continuous monitoring for bias and quality control. Through ongoing model updates and strict access controls, we maintain alignment with responsible AI principles while protecting against potential misuse. Users are encouraged to review our Responsible Use Guidelines and implement appropriate safety measures based on their specific applications and industry requirements.