From 9dfd3fda52925d9a654e0a5c87c442a7d9ccbe3e Mon Sep 17 00:00:00 2001
From: Katherine Yang <80359429+jbkyang-nvi@users.noreply.github.com>
Date: Wed, 8 Nov 2023 11:15:47 -0800
Subject: [PATCH] Update Popular_Models_Guide/Llama2/trtllm_guide.md

Co-authored-by: Hyunjae Woo <107147848+nv-hwoo@users.noreply.github.com>
---
 Popular_Models_Guide/Llama2/trtllm_guide.md | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/Popular_Models_Guide/Llama2/trtllm_guide.md b/Popular_Models_Guide/Llama2/trtllm_guide.md
index 6b4ef7b2..6f4eb7e3 100644
--- a/Popular_Models_Guide/Llama2/trtllm_guide.md
+++ b/Popular_Models_Guide/Llama2/trtllm_guide.md
@@ -136,7 +136,12 @@ You can test the results of the run with:
 
 ```bash
 # Using the SDK container as an example
-docker run --rm -it --net host --shm-size=2g --ulimit memlock=-1 --ulimit stack=67108864 --gpus all -v /path/to/tensorrtllm_backend:/tensorrtllm_backend -v /path/to/Llama2/repo:/Llama-2-7b-hf -v /path/to/engines:/engines nvcr.io/nvidia/tritonserver:23.10-py3-sdk
+docker run --rm -it --net host --shm-size=2g \
+    --ulimit memlock=-1 --ulimit stack=67108864 --gpus all \
+    -v /path/to/tensorrtllm_backend:/tensorrtllm_backend \
+    -v /path/to/Llama2/repo:/Llama-2-7b-hf \
+    -v /path/to/engines:/engines \
+    nvcr.io/nvidia/tritonserver:23.10-py3-sdk
 # install extra dependencies for the script
 pip3 install transformers sentencepiece
 python3 /tensorrtllm_backend/inflight_batcher_llm/client/inflight_batcher_llm_client.py --request-output-len 200 --tokenizer_type llama --tokenizer_dir /Llama-2-7b-hf