From 8d28dba35deb83a33926135895be786518c6e793 Mon Sep 17 00:00:00 2001
From: Arthur <48595927+ArthurZucker@users.noreply.github.com>
Date: Fri, 26 May 2023 14:30:32 +0200
Subject: [PATCH] [OPT] Doc nit, using fast is fine (#23789)

small doc nit
---
 docs/source/en/model_doc/opt.mdx | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/source/en/model_doc/opt.mdx b/docs/source/en/model_doc/opt.mdx
index 0c041c5ecb..073c7c3bfc 100644
--- a/docs/source/en/model_doc/opt.mdx
+++ b/docs/source/en/model_doc/opt.mdx
@@ -23,7 +23,7 @@ The abstract from the paper is the following:
 
 Tips:
 - OPT has the same architecture as [`BartDecoder`].
-- Contrary to GPT2, OPT adds the EOS token `</s>` to the beginning of every prompt. **Note**: Make sure to pass `use_fast=False` when loading OPT's tokenizer with [`AutoTokenizer`] to get the correct tokenizer.
+- Contrary to GPT2, OPT adds the EOS token `</s>` to the beginning of every prompt.
 
 This model was contributed by [Arthur Zucker](https://huggingface.co/ArthurZ), [Younes Belkada](https://huggingface.co/ybelkada), and [Patrick Von Platen](https://huggingface.co/patrickvonplaten).
 The original code can be found [here](https://github.com/facebookresearch/metaseq).