From f0da0c131b601cc814a590deb22380d58907ebd9 Mon Sep 17 00:00:00 2001
From: Yuwen Hu <54161268+Oscilloscope98@users.noreply.github.com>
Date: Fri, 26 Jan 2024 14:42:11 +0800
Subject: [PATCH] Disable llama2 optimize model true or false test for now in
 Arc UTs (#10008)

---
 .../test/inference_gpu/test_transformers_api_disable_xmx.py    | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/python/llm/test/inference_gpu/test_transformers_api_disable_xmx.py b/python/llm/test/inference_gpu/test_transformers_api_disable_xmx.py
index 7afce417..6f895a6b 100644
--- a/python/llm/test/inference_gpu/test_transformers_api_disable_xmx.py
+++ b/python/llm/test/inference_gpu/test_transformers_api_disable_xmx.py
@@ -27,7 +27,8 @@ prompt = "Once upon a time, there existed a little girl who liked to have advent
 
 @pytest.mark.parametrize('Model, Tokenizer, model_path',[
     (AutoModelForCausalLM, AutoTokenizer, os.environ.get('MPT_7B_ORIGIN_PATH')),
-    (AutoModelForCausalLM, AutoTokenizer, os.environ.get('LLAMA2_7B_ORIGIN_PATH'))
+    # (AutoModelForCausalLM, AutoTokenizer, os.environ.get('LLAMA2_7B_ORIGIN_PATH')),
+    (AutoModelForCausalLM, AutoTokenizer, os.environ.get('FALCON_7B_ORIGIN_PATH')),
     ])
 def test_optimize_model(Model, Tokenizer, model_path):
     with torch.inference_mode():