Model Distillation Python Packages

autodistill

Images to inference with no labeling (use foundation models to train supervised models).

insurance-distill

Distil GBM models into multiplicative GLM factor tables for insurance rating engines.

autodistill-gcp-vision

Autodistill Google Cloud Vision module for use in training a custom, fine-tuned model.

llm-distiller

Model distiller automator — recursively drives an LLM with seed prompts and stores compressed outputs in SQLite

autodistill-rekognition

AWS Rekognition base model for use with Autodistill

autodistll-grounded-sam

Automatically distill large foundational models into smaller, in-domain models for deployment

darklight

A library for accelerating knowledge distillation training