From cea9ec086a14da1320940c5e48d7bd5dbcf32734 Mon Sep 17 00:00:00 2001
From: Fanli Lin <fanli.lin@intel.com>
Date: Thu, 12 Sep 2024 00:56:55 +0800
Subject: [PATCH] [docs] add the missing tokenizer when pushing models to
 huggingface hub (#33428)

* add tokenizer

* typo
---
 docs/source/en/tasks/language_modeling.md        | 1 +
 docs/source/en/tasks/masked_language_modeling.md | 1 +
 2 files changed, 2 insertions(+)

diff --git a/docs/source/en/tasks/language_modeling.md b/docs/source/en/tasks/language_modeling.md
index fab9828ab20770..119026cd03f366 100644
--- a/docs/source/en/tasks/language_modeling.md
+++ b/docs/source/en/tasks/language_modeling.md
@@ -253,6 +253,7 @@ At this point, only three steps remain:
 ...     train_dataset=lm_dataset["train"],
 ...     eval_dataset=lm_dataset["test"],
 ...     data_collator=data_collator,
+...     tokenizer=tokenizer,
 ... )
 
 >>> trainer.train()
diff --git a/docs/source/en/tasks/masked_language_modeling.md b/docs/source/en/tasks/masked_language_modeling.md
index 5987e0193f10a8..469b1d7fcb99f6 100644
--- a/docs/source/en/tasks/masked_language_modeling.md
+++ b/docs/source/en/tasks/masked_language_modeling.md
@@ -245,6 +245,7 @@ At this point, only three steps remain:
 ...     train_dataset=lm_dataset["train"],
 ...     eval_dataset=lm_dataset["test"],
 ...     data_collator=data_collator,
+...     tokenizer=tokenizer,
 ... )
 
 >>> trainer.train()