diff --git a/README.md b/README.md
index e1391e39b..f8f226963 100644
--- a/README.md
+++ b/README.md
@@ -171,6 +171,9 @@ base_model_ignore_patterns:
 # if the base_model repo on hf hub doesn't include configuration .json files,
 # you can set that here, or leave this empty to default to base_model
 base_model_config: ./llama-7b-hf
+# Optional tokenizer configuration override in case you want to use a different tokenizer
+# than the one defined in the base model
+tokenizer_config:
 # If you want to specify the type of model to load, AutoModelForCausalLM is a good choice too
 model_type: AutoModelForCausalLM
 # Corresponding tokenizer for the model AutoTokenizer is a good choice
diff --git a/src/axolotl/utils/models.py b/src/axolotl/utils/models.py
index dc303bca6..cf351a78d 100644
--- a/src/axolotl/utils/models.py
+++ b/src/axolotl/utils/models.py
@@ -30,7 +30,6 @@ from axolotl.prompt_tokenizers import LLAMA_DEFAULT_PAD_TOKEN
 
 if TYPE_CHECKING:
     from peft import PeftConfig  # noqa: F401
-    from transformers import PreTrainedTokenizer  # noqa: F401
 
     from axolotl.utils.dict import DictDefault  # noqa: F401