Update README.md

README.md

@@ -87,7 +87,7 @@ The model was evaluated on GSM8K and GPQA-Diamond-CoT benchmarks.
 
 ### Reproduction
 
-The above evaluation results were obtained using the `lm-evaluation-harness` framework, based on the Docker image `rocm/vllm-dev:nightly_main_20260712`, with vLLM pre-installed inside the image and lm-eval compiled and installed from source.
+The above evaluation results were obtained using the `lm-evaluation-harness` framework, based on the Docker image `rocm/vllm-dev:nightly_main_20260712`, with vLLM and lm-eval compiled and installed from source.
 
 ```
 export VLLM_ROCM_USE_AITER=1