Codemod examples/models/llama2 to examples/models/llama (#6302)

Summary:
Pull Request resolved: #6302

Pull Request resolved: #6275

Squash of D64446460, D64446461, D64446462, D64446459

allow-large-files
bypass-github-export-checks
bypass-github-pytorch-ci-checks
bypass-github-executorch-ci-checks
bypass-github-torchtune-ci-checks

Reviewed By: iseeyuan

Differential Revision: D64446900

fbshipit-source-id: f3cfe3d049470581ca1636042fd89f1c4fac2726

Author: mergennachin

.ci/scripts/build_llama_android.sh

@@ -48,9 +48,9 @@ build_llama_runner() {
     -DEXECUTORCH_BUILD_KERNELS_OPTIMIZED=ON \
     -DEXECUTORCH_BUILD_KERNELS_QUANTIZED=ON \
     -DEXECUTORCH_BUILD_KERNELS_CUSTOM=ON \
-    -Bcmake-android-out/examples/models/llama2 examples/models/llama2
+    -Bcmake-android-out/examples/models/llama examples/models/llama
 
-    cmake --build cmake-android-out/examples/models/llama2 -j4 --config Release
+    cmake --build cmake-android-out/examples/models/llama -j4 --config Release
 }
 install_flatc_from_source
 install_executorch_and_backend_lib

.ci/scripts/test_llama.sh

@@ -125,7 +125,7 @@ cmake_install_executorch_libraries() {
 
 cmake_build_llama_runner() {
     echo "Building llama runner"
-    dir="examples/models/llama2"
+    dir="examples/models/llama"
     retry cmake \
         -DCMAKE_INSTALL_PREFIX=cmake-out \
         -DCMAKE_BUILD_TYPE=Debug \
@@ -206,7 +206,7 @@ if [[ "${QNN}" == "ON" ]]; then
   EXPORT_ARGS="${EXPORT_ARGS} -kv -v --qnn --disable_dynamic_shape"
 fi
 # Add dynamically linked library location
-$PYTHON_EXECUTABLE -m examples.models.llama2.export_llama ${EXPORT_ARGS}
+$PYTHON_EXECUTABLE -m examples.models.llama.export_llama ${EXPORT_ARGS}
 
 # Create tokenizer.bin.
 echo "Creating tokenizer.bin"
@@ -219,15 +219,15 @@ echo "Running ${EXPORTED_MODEL_NAME} in portable mode"
 if [[ "${BUILD_TOOL}" == "buck2" ]]; then
   # Run model.
   # shellcheck source=/dev/null
-  $BUCK run examples/models/llama2:main -- ${RUNTIME_ARGS} > result.txt
+  $BUCK run examples/models/llama:main -- ${RUNTIME_ARGS} > result.txt
 elif [[ "${BUILD_TOOL}" == "cmake" ]]; then
   cmake_install_executorch_libraries
   cmake_build_llama_runner
   # Run llama runner
   NOW=$(date +"%H:%M:%S")
   echo "Starting to run llama runner at ${NOW}"
   # shellcheck source=/dev/null
-  cmake-out/examples/models/llama2/llama_main ${RUNTIME_ARGS} > result.txt
+  cmake-out/examples/models/llama/llama_main ${RUNTIME_ARGS} > result.txt
   NOW=$(date +"%H:%M:%S")
   echo "Finished at ${NOW}"
 else

.ci/scripts/test_model.sh

@@ -75,9 +75,9 @@ run_portable_executor_runner() {
 test_model() {
   if [[ "${MODEL_NAME}" == "llama2" ]]; then
     # Install requirements for export_llama
-    bash examples/models/llama2/install_requirements.sh
-    # Test export_llama script: python3 -m examples.models.llama2.export_llama
-    "${PYTHON_EXECUTABLE}" -m examples.models.llama2.export_llama -c examples/models/llama2/params/demo_rand_params.pth -p examples/models/llama2/params/demo_config.json
+    bash examples/models/llama/install_requirements.sh
+    # Test export_llama script: python3 -m examples.models.llama.export_llama
+    "${PYTHON_EXECUTABLE}" -m examples.models.llama.export_llama -c examples/models/llama/params/demo_rand_params.pth -p examples/models/llama/params/demo_config.json
     run_portable_executor_runner
     rm "./${MODEL_NAME}.pte"
   fi

.github/workflows/android-perf.yml

@@ -160,7 +160,7 @@ jobs:
 
         if [[ ${{ matrix.model }} =~ ^stories* ]]; then
             # Install requirements for export_llama
-            PYTHON_EXECUTABLE=python bash examples/models/llama2/install_requirements.sh
+            PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
             # Test llama2
             if [[ ${{ matrix.delegate }} == "xnnpack" ]]; then
                 DELEGATE_CONFIG="xnnpack+custom+qe"

.github/workflows/apple-perf.yml

@@ -162,7 +162,7 @@ jobs:
         if [[ ${{ matrix.model }} =~ ^stories* ]]; then
           # Install requirements for export_llama
           PYTHON_EXECUTABLE=python ${CONDA_RUN} --no-capture-output \
-            bash examples/models/llama2/install_requirements.sh
+            bash examples/models/llama/install_requirements.sh
 
           # Test llama2
           if [[ ${{ matrix.delegate }} == "xnnpack" ]]; then

.github/workflows/pull.yml

@@ -123,7 +123,7 @@ jobs:
         # Setup executorch
         PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh buck2
         # Install requirements for export_llama
-        PYTHON_EXECUTABLE=python bash examples/models/llama2/install_requirements.sh
+        PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
         # Test llama2
         PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh stories110M "${BUILD_TOOL}" "${DTYPE}" "${MODE}"
 
@@ -222,7 +222,7 @@ jobs:
         bash install_requirements.sh --pybind xnnpack
 
         # install Llava requirements
-        bash examples/models/llama2/install_requirements.sh
+        bash examples/models/llama/install_requirements.sh
         bash examples/models/llava/install_requirements.sh
 
         # run python unittest
@@ -417,7 +417,7 @@ jobs:
         # Setup executorch
         PYTHON_EXECUTABLE=python bash .ci/scripts/setup-linux.sh buck2
         # Install requirements for export_llama
-        PYTHON_EXECUTABLE=python bash examples/models/llama2/install_requirements.sh
+        PYTHON_EXECUTABLE=python bash examples/models/llama/install_requirements.sh
         # Test llama2
         PYTHON_EXECUTABLE=python bash .ci/scripts/test_llama.sh stories110M "${BUILD_TOOL}" "${DTYPE}" "${MODE}"
 

.github/workflows/trunk.yml

@@ -257,7 +257,7 @@ jobs:
         fi
 
         # Install requirements for export_llama
-        PYTHON_EXECUTABLE=python ${CONDA_RUN} bash examples/models/llama2/install_requirements.sh
+        PYTHON_EXECUTABLE=python ${CONDA_RUN} bash examples/models/llama/install_requirements.sh
         # Test llama2
         PYTHON_EXECUTABLE=python ${CONDA_RUN} bash .ci/scripts/test_llama.sh stories110M cmake "${DTYPE}" "${MODE}"
 
@@ -281,7 +281,7 @@ jobs:
   #       GITHUB_RUNNER=1 PYTHON_EXECUTABLE=python ${CONDA_RUN} bash .ci/scripts/setup-macos.sh "${BUILD_TOOL}"
 
   #       # install Llava requirements
-  #       ${CONDA_RUN} bash examples/models/llama2/install_requirements.sh
+  #       ${CONDA_RUN} bash examples/models/llama/install_requirements.sh
   #       ${CONDA_RUN} bash examples/models/llava/install_requirements.sh
 
   #       # run python unittest
@@ -387,7 +387,7 @@ jobs:
         cmake --build cmake-out -j9 --target install --config Release
 
         echo "Build llama runner"
-        dir="examples/models/llama2"
+        dir="examples/models/llama"
         cmake \
             -DCMAKE_INSTALL_PREFIX=cmake-out \
             -DCMAKE_BUILD_TYPE=Release \
@@ -439,5 +439,5 @@ jobs:
 
         python -m extension.export_util.export_hf_model -hfm=${{ matrix.hf_model_repo }} -o ${ET_MODEL_NAME}
 
-        cmake-out/examples/models/llama2/llama_main --model_path=${ET_MODEL_NAME}.pte --tokenizer_path=${TOKENIZER_BIN_FILE} --prompt="My name is"
+        cmake-out/examples/models/llama/llama_main --model_path=${ET_MODEL_NAME}.pte --tokenizer_path=${TOKENIZER_BIN_FILE} --prompt="My name is"
         echo "::endgroup::"

README.md

@@ -22,10 +22,10 @@ please visit our documentation website [for the latest release](https://pytorch.
 
 Check out the [Getting Started](https://pytorch.org/executorch/stable/getting-started-setup.html#quick-setup-colab-jupyter-notebook-prototype) page for a quick spin.
 
-Check out the examples of [Llama](./examples/models/llama2/README.md), [Llava](./examples/models/llava/README.md) and [other models](./examples/README.md) running on edge devices using ExecuTorch.
+Check out the examples of [Llama](./examples/models/llama/README.md), [Llava](./examples/models/llava/README.md) and [other models](./examples/README.md) running on edge devices using ExecuTorch.
 
 
-**[UPDATE - 09/25]** We have added support for running [Llama 3.2 1B/3B](./examples/models/llama2/README.md) models via ExecuTorch.
+**[UPDATE - 09/25]** We have added support for running [Llama 3.2 1B/3B](./examples/models/llama/README.md) models via ExecuTorch.
 
 ## Feedback
 

backends/qualcomm/runtime/targets.bzl

@@ -53,7 +53,7 @@ def define_common_targets():
             exclude = ["Logging.h"],
         ),
         define_static_target = True,
-        link_whole = True,  # needed for executorch/examples/models/llama2:main to register QnnBackend
+        link_whole = True,  # needed for executorch/examples/models/llama:main to register QnnBackend
         platforms = [ANDROID],
         visibility = ["@EXECUTORCH_CLIENTS"],
         resources = {

backends/qualcomm/tests/test_qnn_delegate.py

@@ -37,10 +37,7 @@
     skip_annotation,
 )
 
-from executorch.examples.models.llama2.llama_transformer import (
-    ModelArgs,
-    MOEFeedForward,
-)
+from executorch.examples.models.llama.llama_transformer import ModelArgs, MOEFeedForward
 
 from executorch.examples.qualcomm.utils import setup_common_args_and_variables
 
@@ -51,7 +48,7 @@
 from executorch.examples.models.inception_v3 import InceptionV3Model
 from executorch.examples.models.inception_v4 import InceptionV4Model
 
-# from executorch.examples.models.llama2 import Llama2Model
+# from executorch.examples.models.llama import Llama2Model
 from executorch.examples.models.mobilebert import MobileBertModelExample
 from executorch.examples.models.mobilenet_v2 import MV2Model
 from executorch.examples.models.mobilenet_v3 import MV3Model