diff --git a/trl/trainer/alignprop_trainer.py b/trl/trainer/alignprop_trainer.py
index a4fb473f28..80c9e0556d 100644
--- a/trl/trainer/alignprop_trainer.py
+++ b/trl/trainer/alignprop_trainer.py
@@ -402,10 +402,10 @@ def create_model_card(
         Creates a draft of a model card using the information available to the `Trainer`.
 
         Args:
-            model_name (`str`, *optional*, defaults to `None`):
-                The name of the model.
-            dataset_name (`str`, *optional*, defaults to `None`):
-                The name of the dataset used for training.
+            model_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the model.
+            dataset_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the dataset used for training.
             tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                 Tags to be associated with the model card.
         """
diff --git a/trl/trainer/bco_trainer.py b/trl/trainer/bco_trainer.py
index 8b7c28f9bf..ccbb701d9f 100644
--- a/trl/trainer/bco_trainer.py
+++ b/trl/trainer/bco_trainer.py
@@ -1493,11 +1493,11 @@ def create_model_card(
         Creates a draft of a model card using the information available to the `Trainer`.
 
         Args:
-            model_name (`str`, *optional*, defaults to `None`):
-                The name of the model.
-            dataset_name (`str`, *optional*, defaults to `None`):
-                The name of the dataset used for training.
-            tags (`str`, `list[str]` or None, *optional*, defaults to `None`):
+            model_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the model.
+            dataset_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the dataset used for training.
+            tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                 Tags to be associated with the model card.
         """
         if not self.is_world_process_zero():
diff --git a/trl/trainer/cpo_trainer.py b/trl/trainer/cpo_trainer.py
index a68a8f635b..050dddad99 100644
--- a/trl/trainer/cpo_trainer.py
+++ b/trl/trainer/cpo_trainer.py
@@ -1026,10 +1026,10 @@ def create_model_card(
         Creates a draft of a model card using the information available to the `Trainer`.
 
         Args:
-            model_name (`str`, *optional*, defaults to `None`):
-                The name of the model.
-            dataset_name (`str`, *optional*, defaults to `None`):
-                The name of the dataset used for training.
+            model_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the model.
+            dataset_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the dataset used for training.
             tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                 Tags to be associated with the model card.
         """
diff --git a/trl/trainer/ddpo_trainer.py b/trl/trainer/ddpo_trainer.py
index c4d86d35d2..0ba0c7b642 100644
--- a/trl/trainer/ddpo_trainer.py
+++ b/trl/trainer/ddpo_trainer.py
@@ -603,10 +603,10 @@ def create_model_card(
         Creates a draft of a model card using the information available to the `Trainer`.
 
         Args:
-            model_name (`str`, *optional*, defaults to `None`):
-                The name of the model.
-            dataset_name (`str`, *optional*, defaults to `None`):
-                The name of the dataset used for training.
+            model_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the model.
+            dataset_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the dataset used for training.
             tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                 Tags to be associated with the model card.
         """
diff --git a/trl/trainer/dpo_trainer.py b/trl/trainer/dpo_trainer.py
index b9adbedf5f..d4b197362c 100644
--- a/trl/trainer/dpo_trainer.py
+++ b/trl/trainer/dpo_trainer.py
@@ -1525,10 +1525,10 @@ def create_model_card(
         Creates a draft of a model card using the information available to the `Trainer`.
 
         Args:
-            model_name (`str`, *optional*, defaults to `None`):
-                The name of the model.
-            dataset_name (`str`, *optional*, defaults to `None`):
-                The name of the dataset used for training.
+            model_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the model.
+            dataset_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the dataset used for training.
             tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                 Tags to be associated with the model card.
         """
diff --git a/trl/trainer/gkd_trainer.py b/trl/trainer/gkd_trainer.py
index 74bceba0ee..59d71d1e44 100644
--- a/trl/trainer/gkd_trainer.py
+++ b/trl/trainer/gkd_trainer.py
@@ -346,10 +346,10 @@ def create_model_card(
         Creates a draft of a model card using the information available to the `Trainer`.
 
         Args:
-            model_name (`str`, *optional*, defaults to `None`):
-                The name of the model.
-            dataset_name (`str`, *optional*, defaults to `None`):
-                The name of the dataset used for training.
+            model_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the model.
+            dataset_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the dataset used for training.
             tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                 Tags to be associated with the model card.
         """
diff --git a/trl/trainer/iterative_sft_trainer.py b/trl/trainer/iterative_sft_trainer.py
index 5b88e8a1ce..369348a789 100644
--- a/trl/trainer/iterative_sft_trainer.py
+++ b/trl/trainer/iterative_sft_trainer.py
@@ -405,10 +405,10 @@ def create_model_card(
         Creates a draft of a model card using the information available to the `Trainer`.
 
         Args:
-            model_name (`str`, *optional*, defaults to `None`):
-                The name of the model.
-            dataset_name (`str`, *optional*, defaults to `None`):
-                The name of the dataset used for training.
+            model_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the model.
+            dataset_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the dataset used for training.
             tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                 Tags to be associated with the model card.
         """
diff --git a/trl/trainer/kto_trainer.py b/trl/trainer/kto_trainer.py
index d851a92ab3..897ce25520 100644
--- a/trl/trainer/kto_trainer.py
+++ b/trl/trainer/kto_trainer.py
@@ -1501,10 +1501,10 @@ def create_model_card(
         Creates a draft of a model card using the information available to the `Trainer`.
 
         Args:
-            model_name (`str`, *optional*, defaults to `None`):
-                The name of the model.
-            dataset_name (`str`, *optional*, defaults to `None`):
-                The name of the dataset used for training.
+            model_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the model.
+            dataset_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the dataset used for training.
             tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                 Tags to be associated with the model card.
         """
diff --git a/trl/trainer/nash_md_trainer.py b/trl/trainer/nash_md_trainer.py
index 0d04193524..cbe218066e 100644
--- a/trl/trainer/nash_md_trainer.py
+++ b/trl/trainer/nash_md_trainer.py
@@ -468,10 +468,10 @@ def create_model_card(
         Creates a draft of a model card using the information available to the `Trainer`.
 
         Args:
-            model_name (`str`, *optional*, defaults to `None`):
-                The name of the model.
-            dataset_name (`str`, *optional*, defaults to `None`):
-                The name of the dataset used for training.
+            model_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the model.
+            dataset_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the dataset used for training.
             tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                 Tags to be associated with the model card.
         """
@@ -492,7 +492,7 @@ def create_model_card(
 
         citation = textwrap.dedent("""\
         @inproceedings{munos2024nash,
-            title        = {Nash Learning from Human Feedback},
+            title        = {{Nash Learning from Human Feedback}},
             author       = {R{\'{e}}mi Munos and Michal Valko and Daniele Calandriello and Mohammad Gheshlaghi Azar and Mark Rowland and Zhaohan Daniel Guo and Yunhao Tang and Matthieu Geist and Thomas Mesnard and C{\\^{o}}me Fiegel and Andrea Michi and Marco Selvi and Sertan Girgin and Nikola Momchev and Olivier Bachem and Daniel J. Mankowitz and Doina Precup and Bilal Piot},
             year         = 2024,
             booktitle    = {Forty-first International Conference on Machine Learning, {ICML} 2024, Vienna, Austria, July 21-27, 2024},
diff --git a/trl/trainer/online_dpo_trainer.py b/trl/trainer/online_dpo_trainer.py
index 35d9394e3f..c3509caa52 100644
--- a/trl/trainer/online_dpo_trainer.py
+++ b/trl/trainer/online_dpo_trainer.py
@@ -778,10 +778,10 @@ def create_model_card(
         Creates a draft of a model card using the information available to the `Trainer`.
 
         Args:
-            model_name (`str`, *optional*, defaults to `None`):
-                The name of the model.
-            dataset_name (`str`, *optional*, defaults to `None`):
-                The name of the dataset used for training.
+            model_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the model.
+            dataset_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the dataset used for training.
             tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                 Tags to be associated with the model card.
         """
diff --git a/trl/trainer/orpo_trainer.py b/trl/trainer/orpo_trainer.py
index 803bda6699..06457683e8 100644
--- a/trl/trainer/orpo_trainer.py
+++ b/trl/trainer/orpo_trainer.py
@@ -1055,10 +1055,10 @@ def create_model_card(
         Creates a draft of a model card using the information available to the `Trainer`.
 
         Args:
-            model_name (`str`, *optional*, defaults to `None`):
-                The name of the model.
-            dataset_name (`str`, *optional*, defaults to `None`):
-                The name of the dataset used for training.
+            model_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the model.
+            dataset_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the dataset used for training.
             tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                 Tags to be associated with the model card.
         """
diff --git a/trl/trainer/ppo_trainer.py b/trl/trainer/ppo_trainer.py
index c30813a4b1..fe3ea3a147 100644
--- a/trl/trainer/ppo_trainer.py
+++ b/trl/trainer/ppo_trainer.py
@@ -747,10 +747,10 @@ def create_model_card(
         Creates a draft of a model card using the information available to the `Trainer`.
 
         Args:
-            model_name (`str`, *optional*, defaults to `None`):
-                The name of the model.
-            dataset_name (`str`, *optional*, defaults to `None`):
-                The name of the dataset used for training.
+            model_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the model.
+            dataset_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the dataset used for training.
             tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                 Tags to be associated with the model card.
         """
diff --git a/trl/trainer/prm_trainer.py b/trl/trainer/prm_trainer.py
index 55a36ca6d8..661c6553f6 100644
--- a/trl/trainer/prm_trainer.py
+++ b/trl/trainer/prm_trainer.py
@@ -288,11 +288,12 @@ def create_model_card(
     ):
         """
         Creates a draft of a model card using the information available to the `Trainer`.
+
         Args:
-            model_name (`str`, *optional*, defaults to `None`):
-                The name of the model.
-            dataset_name (`str`, *optional*, defaults to `None`):
-                The name of the dataset used for training.
+            model_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the model.
+            dataset_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the dataset used for training.
             tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                 Tags to be associated with the model card.
         """
@@ -313,7 +314,7 @@ def create_model_card(
 
         citation = textwrap.dedent("""\
         @article{uesato2022solving,
-            title        = {Solving Math Word Problems With Process- and Outcome-Based Feedback},
+            title        = {{Solving Math Word Problems With Process- and Outcome-Based Feedback}},
             author       = {Uesato, Jonathan and Kushman, Nate and Kumar, Ramana and Song, Francis and Siegel, Noah and Wang, Lisa and Creswell, Antonia and Irving, Geoffrey and Higgins, Irina},
             year         = 2022,
             journal      = {arXiv preprint arXiv:2211.14275}
diff --git a/trl/trainer/reward_trainer.py b/trl/trainer/reward_trainer.py
index 6cbff41281..f7f1fe6e9e 100644
--- a/trl/trainer/reward_trainer.py
+++ b/trl/trainer/reward_trainer.py
@@ -382,10 +382,10 @@ def create_model_card(
         Creates a draft of a model card using the information available to the `Trainer`.
 
         Args:
-            model_name (`str`, *optional*, defaults to `None`):
-                The name of the model.
-            dataset_name (`str`, *optional*, defaults to `None`):
-                The name of the dataset used for training.
+            model_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the model.
+            dataset_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the dataset used for training.
             tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                 Tags to be associated with the model card.
         """
diff --git a/trl/trainer/rloo_trainer.py b/trl/trainer/rloo_trainer.py
index 2e16e6c7f8..ccbda384dc 100644
--- a/trl/trainer/rloo_trainer.py
+++ b/trl/trainer/rloo_trainer.py
@@ -613,10 +613,10 @@ def create_model_card(
         Creates a draft of a model card using the information available to the `Trainer`.
 
         Args:
-            model_name (`str`, *optional*, defaults to `None`):
-                The name of the model.
-            dataset_name (`str`, *optional*, defaults to `None`):
-                The name of the dataset used for training.
+            model_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the model.
+            dataset_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the dataset used for training.
             tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                 Tags to be associated with the model card.
         """
diff --git a/trl/trainer/sft_trainer.py b/trl/trainer/sft_trainer.py
index fdd5b88453..9e2e5fe04f 100644
--- a/trl/trainer/sft_trainer.py
+++ b/trl/trainer/sft_trainer.py
@@ -512,10 +512,10 @@ def create_model_card(
         Creates a draft of a model card using the information available to the `Trainer`.
 
         Args:
-            model_name (`str`, *optional*, defaults to `None`):
-                The name of the model.
-            dataset_name (`str`, *optional*, defaults to `None`):
-                The name of the dataset used for training.
+            model_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the model.
+            dataset_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the dataset used for training.
             tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                 Tags to be associated with the model card.
         """
diff --git a/trl/trainer/xpo_trainer.py b/trl/trainer/xpo_trainer.py
index 212b73cba5..2d535344e7 100644
--- a/trl/trainer/xpo_trainer.py
+++ b/trl/trainer/xpo_trainer.py
@@ -525,10 +525,10 @@ def create_model_card(
         Creates a draft of a model card using the information available to the `Trainer`.
 
         Args:
-            model_name (`str`, *optional*, defaults to `None`):
-                The name of the model.
-            dataset_name (`str`, *optional*, defaults to `None`):
-                The name of the dataset used for training.
+            model_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the model.
+            dataset_name (`str` or `None`, *optional*, defaults to `None`):
+                Name of the dataset used for training.
             tags (`str`, `list[str]` or `None`, *optional*, defaults to `None`):
                 Tags to be associated with the model card.
         """