brainwires-training 0.9.0

Model training and fine-tuning for the Brainwires Agent Framework — cloud fine-tuning and local LoRA/QLoRA/DoRA training
Documentation 
1
2
3
4
5
6
7

/// Direct Preference Optimization (DPO) loss implementation.
pub mod dpo;
/// Odds Ratio Preference Optimization (ORPO) loss implementation.
pub mod orpo;

pub use dpo::DpoLoss;
pub use orpo::OrpoLoss;