From e246f1e258402d890f9747ffe75f4fe76f9b2670 Mon Sep 17 00:00:00 2001
From: Yina Chen <33650826+cyita@users.noreply.github.com>
Date: Tue, 27 Aug 2024 08:03:18 +0300
Subject: [PATCH] update llama3 npu example (#11933)

---
 .../NPU/HF-Transformers-AutoModels/LLM/README.md  | 15 +++++++++++----
 .../LLM/{llama2.py => llama.py}                   |  0
 2 files changed, 11 insertions(+), 4 deletions(-)
 rename python/llm/example/NPU/HF-Transformers-AutoModels/LLM/{llama2.py => llama.py} (100%)

diff --git a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/README.md b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/README.md
index 52d71ed4..80c82880 100644
--- a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/README.md
+++ b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/README.md
@@ -78,12 +78,16 @@ done
 
 ## 4. Run Optimized Models (Experimental)
 The example below shows how to run the **_optimized model implementations_** on Intel NPU, including
-- [Llama2-7B](./llama2.py)
+- [Llama2-7B](./llama.py)
+- [Llama3-8B](./llama.py)
 - [Qwen2-1.5B](./qwen2.py)
 
-```
+```bash
 # to run Llama-2-7b-chat-hf
-python llama2.py
+python llama.py
+
+# to run Meta-Llama-3-8B-Instruct
+python llama.py --repo-id-or-model-path meta-llama/Meta-Llama-3-8B-Instruct
 
 # to run Qwen2-1.5B-Instruct
 python qwen2.py
@@ -102,7 +106,10 @@ Arguments info:
 If you encounter output problem, please try to disable the optimization of transposing value cache with following command:
 ```bash
 # to run Llama-2-7b-chat-hf
-python  llama2.py --disable-transpose-value-cache
+python  llama.py --disable-transpose-value-cache
+
+# to run Meta-Llama-3-8B-Instruct
+python llama.py --repo-id-or-model-path meta-llama/Meta-Llama-3-8B-Instruct --disable-transpose-value-cache
 
 # to run Qwen2-1.5B-Instruct
 python qwen2.py --disable-transpose-value-cache
diff --git a/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/llama2.py b/python/llm/example/NPU/HF-Transformers-AutoModels/LLM/llama.py
similarity index 100%
rename from python/llm/example/NPU/HF-Transformers-AutoModels/LLM/llama2.py
rename to python/llm/example/NPU/HF-Transformers-AutoModels/LLM/llama.py