diff --git a/.github/workflows/llama_cpp_plugin_build_and_test.yml b/.github/workflows/llama_cpp_plugin_build_and_test.yml
index ae239085d..cf2ffe36e 100644
--- a/.github/workflows/llama_cpp_plugin_build_and_test.yml
+++ b/.github/workflows/llama_cpp_plugin_build_and_test.yml
@@ -4,6 +4,7 @@ on:
   pull_request:
     paths:
       - 'modules/llama_cpp_plugin/**'
+      - '.github/workflows/llama_cpp_plugin_build_and_test.yml'
 
 permissions: read-all
 
@@ -58,12 +59,16 @@ jobs:
           repository: ggerganov/llama.cpp
           path: llama.cpp
 
+      - uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+
       - name: Prepare test data - convert test model files
         run: |
-          pip install -r llama.cpp/requirements/requirements-convert-hf-to-gguf.txt
+          python3 -m pip install -r llama.cpp/requirements/requirements-convert_hf_to_gguf.txt
           huggingface-cli download gpt2 model.safetensors tokenizer.json tokenizer_config.json vocab.json config.json merges.txt --local-dir hf_gpt2
           mkdir -p ${{ github.workspace }}/test_data
-          python3 llama.cpp/convert-hf-to-gguf.py hf_gpt2 --outtype f32 --outfile ${{ github.workspace }}/test_data/gpt2.gguf
+          python3 llama.cpp/convert_hf_to_gguf.py hf_gpt2 --outtype f32 --outfile ${{ github.workspace }}/test_data/gpt2.gguf
 
       - name: Install libtbb2
         run: |