From 8e0817c262da5c104f651a0ce4ac9ee0cd76f4ce Mon Sep 17 00:00:00 2001
From: Roger Wang <136131678+ywang96@users.noreply.github.com>
Date: Mon, 1 Jul 2024 15:09:11 -0700
Subject: [PATCH] [Bugfix][Doc] Fix Doc Formatting (#6048)

---
 docs/source/serving/faq.rst | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/docs/source/serving/faq.rst b/docs/source/serving/faq.rst
index daa81d7c8c9c3..7b0374be8adff 100644
--- a/docs/source/serving/faq.rst
+++ b/docs/source/serving/faq.rst
@@ -1,5 +1,5 @@
 Frequently Asked Questions
-========================
+===========================
 
     Q: How can I serve multiple models on a single port using the OpenAI API?
 
@@ -9,4 +9,4 @@ A: Assuming that you're referring to using OpenAI compatible server to serve mul
 
     Q: Which model to use for offline inference embedding?
 
-A: If you want to use an embedding model, try: https://huggingface.co/intfloat/e5-mistral-7b-instruct. Instead models, such as Llama-3-8b, Mistral-7B-Instruct-v0.3, are generation models rather than an embedding model
\ No newline at end of file
+A: If you want to use an embedding model, try: https://huggingface.co/intfloat/e5-mistral-7b-instruct. Instead models, such as Llama-3-8b, Mistral-7B-Instruct-v0.3, are generation models rather than an embedding model