From 34c15d3a101b6748623a9c30e3f5382e58ae6bf4 Mon Sep 17 00:00:00 2001
From: SONG Ge <38711238+sgwhat@users.noreply.github.com>
Date: Tue, 25 Jun 2024 10:17:20 +0800
Subject: [PATCH] update pp document (#11421)

---
 python/llm/example/GPU/Pipeline-Parallel-Inference/README.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/python/llm/example/GPU/Pipeline-Parallel-Inference/README.md b/python/llm/example/GPU/Pipeline-Parallel-Inference/README.md
index 19d14cea..5206767e 100644
--- a/python/llm/example/GPU/Pipeline-Parallel-Inference/README.md
+++ b/python/llm/example/GPU/Pipeline-Parallel-Inference/README.md
@@ -59,6 +59,7 @@ For optimal performance, it is recommended to set several environment variables.
 You could specify `--repo-id-or-model-path` in the test script to be the huggingface repo id for Llama2 / Llama3 to be downloaded, or the path to the huggingface checkpoint folder. Besides, you could change `NUM_GPUS` to the number of GPUs you have on your machine.
 
 ```bash
+pip install transformers==4.37.0
 bash run_llama_arc_2_card.sh
 ```
 
@@ -167,6 +168,7 @@ bash run_yi_arc_2_card.sh
 You could specify `--repo-id-or-model-path` in the test script to be the huggingface repo id for Codellama to be downloaded, or the path to the huggingface checkpoint folder. Besides, you could change `NUM_GPUS` to the number of GPUs you have on your machine.
 
 ```bash
+pip install transformers==4.37.0
 bash run_codellama_arc_2_card.sh
 ```
 
@@ -182,6 +184,7 @@ bash run_codellama_arc_2_card.sh
 You could specify `--repo-id-or-model-path` in the test script to be the huggingface repo id for Solar to be downloaded, or the path to the huggingface checkpoint folder. Besides, you could change `NUM_GPUS` to the number of GPUs you have on your machine.
 
 ```bash
+pip install transformers==4.37.0
 bash run_solar_arc_2_card.sh
 ```