diff --git a/docs/source/basic_tutorials/custom_models.md b/docs/source/basic_tutorials/non_core_models.md
similarity index 97%
rename from docs/source/basic_tutorials/custom_models.md
rename to docs/source/basic_tutorials/non_core_models.md
index ec852e36..f6a8dc8e 100644
--- a/docs/source/basic_tutorials/custom_models.md
+++ b/docs/source/basic_tutorials/non_core_models.md
@@ -1,4 +1,4 @@
-# Custom Model Serving
+# Non-core Model Serving
 
 TGI supports various LLM architectures (see full list [here](https://github.com/huggingface/text-generation-inference#optimized-architectures)). If you wish to serve a model that is not one of the supported models, TGI will fallback to transformers implementation of that model. They can be loaded by:
 
@@ -18,4 +18,4 @@ You can serve these models using docker like below 👇
 
 ```bash
 docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:latest --model-id gpt2
-```
\ No newline at end of file
+```