From fe6b0739981be2293d88991270da5032f808487f Mon Sep 17 00:00:00 2001
From: Adam H <74554328+excepto64@users.noreply.github.com>
Date: Tue, 16 Jun 2026 11:50:01 +0100
Subject: [PATCH] Fix lora_combiner docs.

---
 docs/source/common_options.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/source/common_options.rst b/docs/source/common_options.rst
index dd35acb..785dfce 100644
--- a/docs/source/common_options.rst
+++ b/docs/source/common_options.rst
@@ -525,7 +525,7 @@ Only the adapter is saved. Merge it back with the base model to deploy:
       --lora_path ./checkpoint/llama3-8b-rm \
       --output_path ./checkpoint/llama-3-8b-rm-combined \
       --is_rm \
-      --param_dtype bf16
+      --ds.param_dtype bf16
 
 Use ``--is_rm`` when merging a reward model (preserves the score head).