diff --git a/docs/source/developer_guide/evaluation/using_lm_eval.md b/docs/source/developer_guide/evaluation/using_lm_eval.md
index 2e5453c3..fad9c26d 100644
--- a/docs/source/developer_guide/evaluation/using_lm_eval.md
+++ b/docs/source/developer_guide/evaluation/using_lm_eval.md
@@ -106,9 +106,17 @@ Install lm-eval in the container:
 
 ```bash
 export HF_ENDPOINT="https://hf-mirror.com"
+export USE_MODELSCOPE_HUB=0
 pip install lm-eval[api]
 ```
 
+:::{note}
+The Docker container is launched with `VLLM_USE_MODELSCOPE=True`, which may
+cause lm-eval to download datasets from ModelScope instead of HuggingFace.
+Setting `USE_MODELSCOPE_HUB=0` disables this behavior so that lm-eval can
+fetch datasets from HuggingFace correctly.
+:::
+
 Run the following command:
 
 ```shell
@@ -170,9 +178,17 @@ Install lm-eval in the container:
 
 ```bash
 export HF_ENDPOINT="https://hf-mirror.com"
+export USE_MODELSCOPE_HUB=0
 pip install lm-eval
 ```
 
+:::{note}
+The Docker container is launched with `VLLM_USE_MODELSCOPE=True`, which may
+cause lm-eval to download datasets from ModelScope instead of HuggingFace.
+Setting `USE_MODELSCOPE_HUB=0` disables this behavior so that lm-eval can
+fetch datasets from HuggingFace correctly.
+:::
+
 Run the following command:
 
 ```shell