Fix llama2 README.md cmake instructions (#3096)

Summary:

As titled. The current instruction runs into issue due to our way of arranging `pthreadpool` and `cpuinfo` in CMake. Will need a bigger effort to clean them up. For now let's update the instruction to be able to run it.

Differential Revision: D56251563

Author: larryliu0820

examples/models/llama2/README.md

@@ -146,6 +146,7 @@ The Uncyclotext results generated above used: `{max_seq_len: 2048, limit: 1000}`
         -DEXECUTORCH_BUILD_EXTENSION_DATA_LOADER=ON \
         -DEXECUTORCH_BUILD_XNNPACK=ON \
         -DEXECUTORCH_BUILD_OPTIMIZED=ON \
+        -DEXECUTORCH_BUILD_CUSTOM=ON \
         -Bcmake-out .
 
     cmake --build cmake-out -j16 --target install --config Release
@@ -156,7 +157,9 @@ The Uncyclotext results generated above used: `{max_seq_len: 2048, limit: 1000}`
     cmake -DPYTHON_EXECUTABLE=python \
         -DCMAKE_INSTALL_PREFIX=cmake-out \
         -DCMAKE_BUILD_TYPE=Release \
+        -DEXECUTORCH_BUILD_CUSTOM=ON \
         -DEXECUTORCH_BUILD_OPTIMIZED=ON \
+        -DEXECUTORCH_BUILD_XNNPACK=ON \
         -Bcmake-out/examples/models/llama2 \
         examples/models/llama2