Skip to content

Custom Model Training ​

Train Phony to generate data that matches YOUR domain. Works with any language—Turkish, Japanese, or your custom terminology.


How It Works ​

Phony learns statistical patterns from your data, not memorizes it. The trained model generates new data that looks like yours but never reproduces original values.

Your Data → Learn Patterns → Generate Similar (Not Same)

• Learns character/word distributions
• Preserves statistical properties
• Never reproduces original data
• Works with ANY language

Training Sources ​

Open Source (Local) ​

  • Text file (.txt, one item per line) — built today
  • CSV/TSV (any column) — roadmap
  • JSON/JSONL (any field path) — roadmap
bash
# CLI
phony train names.txt -o names.ngram -n 2

# PHP (generation-only port — load and generate; training lives in the CLI)
Phony::loadModel('names.ngram');

Cloud (Additional Sources) ​

  • Database column (MySQL, PostgreSQL, SQLite)
  • API response (fetch & extract)
  • S3/GCS bucket (bulk data)
  • Clipboard/Paste (quick training in Web UI)

Cloud Workflow ​

Training runs on the agent in your infrastructure (local-first): models are stored in your storage, and the control plane keeps only the catalog — name, version, hash. See Cloud Platform.

  1. Connect database or upload file
  2. Select column/field to train from
  3. Configure n-gram size, excludeOriginals, etc.
  4. Preview generated samples in UI
  5. Train & Save model (with version)
  6. Use in sync jobs or download for local use

Model Management ​

  • List all models with stats
  • Generate samples to test model quality
  • Download .ngram file for local/OSS use
  • Share within your team
  • Version history with diff
  • Rollback to previous version
  • Scheduled re-training from live data

Usage Examples ​

bash
# Train locally
$ phony train turkish_names.txt -o turkish.ngram

# Load and use
Phony::loadModel('turkish.ngram');
Phony::model('turkish')->generate(1000);

# In Cloud sync jobs
first_name: phony:model:turkish_names_v1

Tier Limits ​

Local training (CLI, files) is free and unlimited for everyone. Cloud-managed training is the paid layer:

FeatureFREESTARTERTEAMBUSINESS
Local Training (files, CLI)✓ Unlimited✓✓✓
Cloud-managed Models310UnlimitedUnlimited
Database Column Training✗✓✓✓
S3/GCS Training✗✗✓✓
Model Versioning✗Last 5UnlimitedWith diff
Team Sharing✗✗✓✓
Scheduled Re-training✗✗✓✓

Phony Cloud — Documentation & Specification