Skip to main content
LEAP Finetune documentation is coming soon. This feature enables fine-tuning LFM models specifically optimized for edge deployment on mobile and embedded devices.

​
Overview

LEAP Finetune will provide:
  • Streamlined fine-tuning optimized for edge deployment
  • Automatic model optimization for mobile and embedded targets
  • Integration with LEAP SDK for seamless deployment

​
Current Alternatives

While LEAP Finetune is in development, you can fine-tune models using:

TRL

Hugging Face’s training library with LoRA/QLoRA support

Unsloth

Memory-efficient fine-tuning with 2x faster training

​
Workflow for Edge Deployment

After fine-tuning with TRL or Unsloth, prepare your model for edge deployment:
  1. Fine-tune your model using TRL or Unsloth
  2. Convert to edge-optimized format using the Model Bundling Service
  3. Deploy to mobile devices using the LEAP SDK
# Example: Bundle a fine-tuned model for edge deployment
leap-bundle create --model ./my-finetuned-model --target ios

​
Stay Updated