From 98a78ddfe4e40feca179d6092ab8ed80382f0251 Mon Sep 17 00:00:00 2001 From: cell-dame <122996026+dame-cell@users.noreply.github.com> Date: Wed, 27 Nov 2024 04:02:06 +0530 Subject: [PATCH] Fix orpo/dpo trainer (#1286) * change the colab notebook for dpo zephyr and orpo * use original tokenizer * Update README.md * Update README.md --------- Co-authored-by: Daniel Han