fix: post_optimization() call.

main.py

@@ -13,7 +13,9 @@ This Space does the following things:
 * Loads a ResNet50 model from `tf.keras.applications` and serializes it as a SavedModel.
 * Performs optimizations with TensorRT. 
 * Runs and displays the benchmarks to compare the throughputs of the native TensorFlow SavedModel and its TensorRT-optimized variant.
-* Optionally, pushes the optimized model to a repository on the Hugging Face Hub. For this to work, one must provide a write-access token (from [hf.co/settings/tokens](hf.co/settings/tokens)) to `your_hf_token`. 
+* Optionally, pushes the optimized model to a repository on the Hugging Face Hub. For this to work, one must provide a write-access token (from hf.co/settings/tokens) to `your_hf_token`. 
+
+As a consequence, you might have to wait for a few minutes to note the results.
 
 ## Notes (important)
 
@@ -68,7 +70,7 @@ def run(hf_token: str) -> str:
     tf_throughput = benchmark(model)
     tf_trt_throughput = benchmark(tensorrt_path)
 
-    benchmark_str = post_optimization(tf_throughput, tf_trt_throughput)
+    benchmark_str = post_optimization([tf_throughput, tf_trt_throughput])
     benchmark_str += "\n"
     benchmark_str += push_to_hub(hf_token, tensorrt_path)