Align KTO with DPO: Remove enforcement of causal language models
Align KTO with DPO: Remove enforcement of causal language models: a task in trl-r2e-v0-1 (Harbor dataset). Title: Align KTO with DPO: Remove enforcement of causal language models
The task
**Title:** Align KTO with DPO: Remove enforcement of causal language models
Part of AdithyaSK/trl-r2e-v0-1.