update README

Signed-off-by: sallyom <[email protected]>

README.md

@@ -9,6 +9,8 @@ Python Library for Evaluation
 
 ## MT-Bench / MT-Bench-Branch Testing Steps
 
+> **⚠️ Note:** Must use Python version 3.11 or later.
+
 ```shell
 # Optional: Use cloud-instance.sh (https://github.com/instructlab/instructlab/tree/main/scripts/infra) to launch and setup the instance
 scripts/infra/cloud-instance.sh ec2 launch -t g5.4xlarge
@@ -27,13 +29,21 @@ pip install -r requirements.txt
 pip install -r requirements-dev.txt
 pip install -e .
 pip install vllm
+
+# Ensure the nvidia-toolkit-setup-service is running
+sudo systemctl status nvidia-toolkit-setup.service
+# If it's not running
+sudo systemctl start nvidia-toolkit-setup.service
+
+# Now start vllm
 python -m vllm.entrypoints.openai.api_server --model instructlab/granite-7b-lab --tensor-parallel-size 1
 ```
 
 In another shell window
 
 ```shell
 export INSTRUCTLAB_EVAL_FIRST_N_QUESTIONS=10 # Optional if you want to shorten run times
+cd eval
 python3 tests/test_gen_answers.py
 python3 tests/test_branch_gen_answers.py
 ```
@@ -104,4 +114,4 @@ eval_output/
         └── reference_answer
             └── instructlab
                 └── granite-7b-lab.jsonl
-```
+```